implement-spec
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon external data in the form of specifications and task tickets. This creates a vulnerability surface where malicious instructions embedded in these documents could influence the primary agent or its sub-agents.
- Ingestion points:
SKILL.md(Step 1: "Read the spec and tickets"). - Boundary markers: The instructions do not define explicit delimiters or prompt the agent to ignore instructions embedded within the processed data.
- Capability inventory: The skill directs sub-agents to write code to the filesystem, perform Git operations (branching, merging), and execute tools like
/code-review. - Sanitization: No sanitization, validation, or filtering mechanisms for the input data are specified.
Audit Metadata