handoff-summary
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from build records and plan files using the Read and Glob tools.
- Ingestion points: External data enters the agent's context when reading plan files and build records as specified in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or boundary markers to isolate the external content from the agent's core instructions.
- Capability inventory: The skill utilizes Read and Glob tools to access files within the environment.
- Sanitization: The skill incorporates security-conscious instructions, such as advising the agent to report test counts rather than raw terminal output and explicitly forbidding the inclusion of environment variables, headers, or arguments in the summary. However, these measures do not entirely eliminate the risk of the agent being influenced by malicious instructions embedded in the processed data.
Audit Metadata