Skip to content
← Registry
Trust Report

permissions-broker

Default mechanism for external data access and third-party actions when local credentials are unavailable. Uses a user-issued Permissions Broker API key (commonly stored as PB_API_KEY) to create approval-gated requests; user approves in Telegram before execution. May store/reuse PB_API_KEY across sessions only with explicit user consent. Currently supported providers: Google, GitHub, and iCloud CALDAV.

78
SUSPICIOUS
Format: openclawScanner: v0.8.0Duration: 20msScanned: 10d ago · Apr 30, 12:58 PMSource →
Embed this badge
AgentVerus SUSPICIOUS 78AgentVerus SUSPICIOUS 78AgentVerus SUSPICIOUS 78
[![AgentVerus](https://agentverus.ai/api/v1/skill/1936d666-087a-4810-8bc6-26e5aab888d2/badge)](https://agentverus.ai/skill/1936d666-087a-4810-8bc6-26e5aab888d2)
Community Discussion

Community Comments

Public comments are the active feedback surface on skill reports right now. Use them to share implementation notes, edge cases, and operator context.

0 comments

Sign in to comment on this skill

No comments yet. Be the first to share your thoughts.

Continue the workflow

Keep this report moving through the activation path: rescan from the submit flow, capture real-world interactions, and wire the trust endpoint into your automation.

https://agentverus.ai/api/v1/skill/1936d666-087a-4810-8bc6-26e5aab888d2/trust
Personalized next commands

Use these current-skill command blocks to keep this exact report moving through your workflow.

Record an interaction
curl -X POST https://agentverus.ai/api/v1/interactions \
  -H "Authorization: Bearer at_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{"agentPlatform":"openclaw","skillId":"1936d666-087a-4810-8bc6-26e5aab888d2","interactedAt":"2026-03-15T12:00:00Z","outcome":"success"}'
Fetch trust JSON
curl https://agentverus.ai/api/v1/skill/1936d666-087a-4810-8bc6-26e5aab888d2/trust

Category Scores

53
Permissions
100
Injection
58
Dependencies
70
Behavioral
90
Content
93
Code Safety

Findings (15)

highCapability contract mismatch: inferred credential access is not declared-15

The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.

Content pattern: access and third-party actions when local credentials are unavailable. Uses a user-issued Permissions Broker API key (commonly stored as PB_API_KEY

Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.

permissionsASST-05
highCapability contract mismatch: inferred command execution is not declared-12

The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.

Content pattern: exec

Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.

permissionsASST-03
highEnvironment variable access + network send (credential harvesting)-7

Code accesses process.env and makes outbound network requests. This combination enables credential harvesting — reading API keys and tokens from the environment and exfiltrating them. (Found in example/documentation code block — reduced severity.)

// const apiKey = process.env.PB_API_KEY!

Review the code for legitimate use. If this is instructional, consider adding a safety disclaimer.

code-safetyASST-05
mediumCapability contract mismatch: inferred file read is not declared-6

The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.

Content pattern: references/

Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.

permissionsASST-03
mediumCapability contract mismatch: inferred network access is not declared-6

The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.

Content pattern: https://permissions-broker.steer.fun

Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.

permissionsASST-04
mediumCapability contract mismatch: inferred documentation ingestion is not declared-8

The scanner inferred a risky capability from the skill content/metadata, but no matching declaration was found. Add a declaration with a clear justification, or remove the behavior.

Content pattern: references/

Declare this capability explicitly in frontmatter permissions with a specific justification, or remove the risky behavior.

permissionsASST-03
mediumThird-party AI provider dependency-8

The skill relies on third-party AI providers or APIs, expanding the remote dependency surface for prompts, inputs, or generated artifacts.

Google Sheets API

Review which external services or providers the skill depends on, what data crosses that boundary, and whether the dependency is necessary for the intended workflow.

dependenciesASST-04
mediumMany external URLs referenced (8)-8

The skill references 8 external URLs and also discusses auth/API/payment workflows, which increases the chance that sensitive operations depend on many remote endpoints.

URLs: https://permissions-broker.steer.fun, https://www.googleapis.com/drive/v3/files?pageSize=5&fields=files(id, https://api.github.com/repos/OWNER/REPO/pulls, https://, https://www.googleapis.com/drive/v3/files?...`...

Minimize external dependencies to reduce supply chain risk.

dependenciesASST-04
mediumFederated auth flow detected-10

Found federated auth flow pattern: "OAuth"

The broker enforces an allowlist and chooses which linked account (OAuth token)

Treat OAuth, 2FA, and token-refresh guidance as authentication-sensitive workflows. Explain scope, storage, and refresh behavior clearly so agents do not handle more credential material than necessary.

behavioralASST-05
mediumUnknown external reference-8

The skill references an unknown external domain which is classified as medium risk. Merged overlapping signals from the repeated finding family: - Unknown external reference

https://api.github.com/repos/OWNER/REPO/pulls

Verify that this external dependency is trustworthy and necessary.

dependenciesASST-04
mediumExternal AI provider delegation detected-10

Found external ai provider delegation pattern: "Google Sheets API"

The broker supports the Google Sheets API host (`sheets.googleapis.com`).

Treat external AI-provider calls as data egress. Make it explicit what prompts, files, or images are sent to third-party providers and require approval before forwarding sensitive content.

behavioralASST-02
mediumExternal tool bridge detected-10

Found external tool bridge pattern: "external service API"

- `upstream_url`: the full external service API URL you want to call

Treat agent tool bridges to external services as privileged capability expansion. Be explicit about reachable systems, auth requirements, and safety boundaries before exposing tools programmatically.

behavioralASST-03
lowUnknown external reference-5

The skill references an unknown external domain which is classified as low risk.

https://permissions-broker.steer.fun

Verify that this external dependency is trustworthy and necessary.

dependenciesASST-04
lowUnknown external reference-5

The skill references an unknown external domain which is classified as low risk.

https://

Verify that this external dependency is trustworthy and necessary.

dependenciesASST-04
infoSafety boundaries defined

The skill includes explicit safety boundaries defining what it should NOT do.

Safety boundary patterns detected in content

Keep these safety boundaries. They improve trust.

contentASST-09