what-else
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to instructions embedded in the data it processes, which could manipulate the agent's analysis or recommendations.
- Ingestion points: According to
SKILL.md, the agent reads project files, outcomes, and feedback, and is instructed to research "consequential external claims" from primary sources. - Boundary markers: The instructions do not specify the use of delimiters or provide directives for the agent to ignore instructions found within the ingested content.
- Capability inventory: The skill relies on the agent's ability to read local file content and utilize research/web-browsing capabilities to synthesize project next steps.
- Sanitization: No validation, escaping, or filtering of content from project files or external sources is required by the instructions.
Audit Metadata