pdm
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from repository sources such as specs, issues, and code files, which could contain instructions meant to manipulate the agent's behavior.\n
- Ingestion points: Data is ingested from files in
docs/,src/, and viaghCLI commands to fetch issue and milestone data.\n - Boundary markers: While the skill uses structured reporting templates, it lacks specific instructions to disregard commands or instructions found within the source material it analyzes.\n
- Capability inventory: The skill has read access to the local file system and network access via the GitHub CLI. It does not perform file writes or execute arbitrary code.\n
- Sanitization: There is no explicit mechanism described for sanitizing or escaping content retrieved from external sources before presenting it in deliverables.
Audit Metadata