resume-blueprint
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to write a file to a path constructed using a directory variable and user-provided input:
$CRACKED_DIR/resume/<company>-blueprint.md. This involves file system interaction where the output path depends on the user's choice of company. - [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted user data (resumes).
- Ingestion points: The skill reads the user's current resume and profile data as primary inputs.
- Boundary markers: The instructions do not specify any delimiters or safety warnings to prevent the agent from executing instructions potentially hidden within the user's resume.
- Capability inventory: The skill possesses file-writing capabilities to the local environment.
- Sanitization: There is no explicit sanitization or validation of the resume content or the company name variable before they are used in file operations.
Audit Metadata