linear-issue-management
Fail
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: HIGHCREDENTIALS_UNSAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The skill instructs the agent to retrieve a specific secret (
course-platform.linear-api-key) from the macOS Keychain using the generic-password service. - [COMMAND_EXECUTION]: The skill requires the execution of
/usr/bin/security find-generic-passwordto access system-stored credentials. - [DATA_EXFILTRATION]: Instructions direct the agent to send the retrieved credential as an Authorization header to
https://api.linear.app/graphql. While this is a well-known service, the programmatic retrieval and transmission of system secrets is a high-risk pattern. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its ingestion of external data.
- Ingestion points: Processes 'approved backlog drafts' and collaborator data (SKILL.md, references/publishing-workflow.md).
- Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded commands within the processed drafts.
- Capability inventory: The agent has access to system credentials via shell command execution and performing network requests.
- Sanitization: There is no evidence of input validation or sanitization for the external draft content before it influences the agent's actions.
Recommendations
- AI detected serious security threats
Audit Metadata