compile-conversation-into-doc
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from conversation files which could contain malicious instructions.
- Ingestion points: Loads and reads all message files (*-user.md and *-ai.md) in a folder as specified in SKILL.md.
- Boundary markers: The instructions in SKILL.md do not specify any delimiters or safety markers to differentiate between the agent's instructions and the content of the conversation files.
- Capability inventory: The skill is instructed to write the compiled results into one or more new Markdown files as described in Step 7 of SKILL.md.
- Sanitization: There are no instructions provided in SKILL.md to sanitize, escape, or filter the content of the ingested files before they are processed or written to output files.
- [NO_CODE]: The skill consists entirely of natural language instructions and does not include any Python or Node.js scripts.
Audit Metadata