distill
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze untrusted external data, creating an attack surface for indirect prompt injection.
- Ingestion points: The skill explicitly targets external sources such as 'a diff, PR, or branch', 'an existing product, subsystem, component, or module', and 'a spec, proposal, or plan' as described in the 'Targets' section of SKILL.md.
- Boundary markers: There are no explicit instructions or delimiters defined to help the agent distinguish between the skill's logic and potentially malicious instructions embedded within the targets being analyzed.
- Capability inventory: The skill utilizes the 'Skill' tool to invoke neighbor skills (e.g., /code-review, /simplify, /zen-review) and has the capability to read project files to find exhibits.
- Sanitization: The methodology does not include steps to sanitize or validate external content before it is processed by the LLM.
Audit Metadata