didyouknow-v2
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from project files and codebases.
- Ingestion points: The skill reads content from various local files, including specifications, implementation plans, task lists, and source code files (e.g., via
--spec,--plan, or--codeflags). - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following malicious commands that might be hidden within the documents being analyzed.
- Capability inventory: The skill instructions grant the agent authority to read files across the project and perform immediate document updates/writes when decisions are reached during the session.
- Sanitization: No sanitization, escaping, or validation of the external file content is performed before it is loaded into the agent's context for 'ultra-deep thinking'.
Audit Metadata