resume-project
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository content, creating a surface for indirect prompt injection.
- Ingestion points: The skill reads various repository files during the Recon phase, including README.md, CONTRIBUTING, ADRs, and planning artifacts (SKILL.md).
- Boundary markers: There are no explicit markers or instructions defined to prevent the agent from following malicious commands that might be embedded in the files it audits.
- Capability inventory: The skill uses filesystem and git tools to read project state, and can execute scripts (e.g., npm, make) after explicit user approval (SKILL.md, examples.md).
- Sanitization: The skill does not specify procedures for sanitizing or escaping data read from the repository before it is used to generate the Reentry Brief.
Audit Metadata