about-docs-folder
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to ingest and follow instructions from project-level files such as
PLAN.mdandAGENTS.md. This architecture creates an indirect prompt injection surface where instructions stored in these files are treated as actionable by the agent.\n - Ingestion points:
docs/plans/**/PLAN.md,docs/plans/**/QA.md, andAGENTS.mdin the project root.\n - Boundary markers: Absent. The templates provided do not include markers to distinguish untrusted file content from system instructions.\n
- Capability inventory: The agent is instructed to modify code, manage checklist states, and perform git operations (commit and push).\n
- Sanitization: The skill provides no mechanisms for sanitizing or validating the content read from these files.
Audit Metadata