posture-readme
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection vulnerability surface (Category 8).\n
- Ingestion points: The skill is triggered for tasks involving the auditing and refactoring of existing
README.mdfiles, which are untrusted external data sources.\n - Boundary markers: There are no delimiters or explicit instructions provided to the agent to distinguish its operational rules from the content within the processed README files.\n
- Capability inventory: The skill's functionality involves the agent reading and restructuring project documentation based on the provided input.\n
- Sanitization: No sanitization, validation, or filtering of the input README content is specified to prevent malicious embedded instructions from influencing agent behavior.
Audit Metadata