brainstorming
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to read current project files, documentation, and commit history. This creates an attack surface where untrusted data (malicious instructions in files) is ingested into the agent's prompt context.
- Ingestion points: The agent is instructed to 'Check out the current project state first (files, docs, recent commits)' in SKILL.md.
- Boundary markers: The skill lacks explicit delimiters or instructions to treat project data as untrusted or to ignore any embedded instructions found within them.
- Capability inventory: The skill can write design plans to the file system ('docs/plans/') and perform git commits (SKILL.md).
- Sanitization: No sanitization or validation of the project data is performed before it is used to generate designs and implementation plans.
Audit Metadata