career-coach
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface.
- Ingestion points: The skill uses the
Readtool to ingest user-provided resumes and professional materials in Phase 1 (SKILL.md). - Boundary markers: The prompt lacks explicit delimiters or specific instructions for the agent to ignore potentially malicious commands embedded within external documents.
- Capability inventory: The skill utilizes the
Readtool to access local files and theWritetool to generate acareer-blueprint.mdfile (SKILL.md). - Sanitization: No sanitization or content validation is performed on the ingested file data.
- [COMMAND_EXECUTION]: File System Interaction.
- The skill uses the
Writetool to create and modify thecareer-blueprint.mdfile in the working directory (SKILL.md). - [EXTERNAL_DOWNLOADS]: References to External Resources.
- The documentation provides instructions for installation via
npxfrom the author's repository and references a related web application hosted on Vercel (README.md). These are standard vendor resources or well-known services.
Audit Metadata