artifact-scan
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the environment, specifically GitHub issue titles and local filenames, which could theoretically contain malicious instructions.
- Ingestion points: The skill reads issue titles via
gh issue list --json number,titleand identifies files matching patterns like./docs/prd-*.md. - Boundary markers: The skill uses a structured markdown report format but does not explicitly instruction the agent to ignore embedded instructions in the metadata it reads.
- Capability inventory: The skill is strictly read-only, limited to
lsandgh issue list. It does not write to the filesystem, perform arbitrary network requests, or execute the content of the files it finds. - Sanitization: No explicit sanitization of issue titles is performed before they are included in the final report.
- Context: The risk is negligible as the skill only uses the data to categorize project state and suggest a routing path. It does not provide an execution path for malicious data.
Audit Metadata