speed-dating
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to adopt project-specific rules from CLAUDE.md and 00- prefixed source-of-truth files. If these files are provided by an untrusted source or modified by a third party, they could contain malicious instructions that override the agent's default behavior or safety guidelines within the context of that project folder.
- Ingestion points: The agent is instructed to read CLAUDE.md and 00- files located in project folders to determine local rules and status.
- Boundary markers: The instructions lack explicit delimiters or warnings to treat these file contents as untrusted data rather than authoritative instructions.
- Capability inventory: The skill facilitates file and directory operations, including creating, renaming, and moving project assets.
- Sanitization: No validation or sanitization of the content within the project-specific configuration files is specified.
Audit Metadata