ketchup
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of plain-text instructions for summarizing information and does not contain any malicious patterns, obfuscation, or unauthorized access attempts.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to process potentially untrusted data from the environment, creating a common attack surface for indirect prompt injection.
- Ingestion points: User messages, subagent reports, and external project metadata such as Pull Request (PR) states and Continuous Integration (CI) logs (SKILL.md).
- Boundary markers: Absent; the prompt does not instruct the agent to use specific delimiters or ignore instructions embedded in the source data.
- Capability inventory: The skill is restricted to reading and summarizing data. The platform-level configuration 'disable-model-invocation: true' prevents the model from executing tools in this context, significantly mitigating potential risks.
- Sanitization: No explicit sanitization or input validation logic is provided within the instructions.
Audit Metadata