jmb-to-spec
Pass
Audited by Gen Agent Trust Hub on Nov 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository and conversation context to generate a specification that is then published externally.
- Ingestion points: The agent is instructed to explore the repository to understand the current state of the codebase and use the current conversation context (SKILL.md).
- Boundary markers: The instructions do not specify any delimiters or safety warnings to ignore instructions that might be embedded in the codebase files or conversation history.
- Capability inventory: The skill possesses file-system read access (repo exploration) and network-write access (publishing to an issue tracker).
- Sanitization: There is no evidence of sanitization or filtering logic to prevent malicious instructions in the analyzed code from influencing the agent's behavior during spec generation.
Audit Metadata