scan-issues
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from GitHub issues (gh issue list) which is an untrusted external source. This data is used for scoring and categorization, meaning malicious instructions embedded in issues could influence the agent's behavior.
- Ingestion points: The output of the
gh issue listcommand in Phase 1 and the analysis of issue labels and content in Phase 2 (SKILL.md). - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing instructions.
- Capability inventory: The skill's capabilities are limited to reading repository information and reporting results; no dangerous file-write, network exfiltration, or privileged execution tools are invoked.
- Sanitization: The instructions do not define any sanitization or validation steps for the content fetched from the GitHub issues before it is analyzed by the agent.
Audit Metadata