format-resume
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
subprocess.runto execute a local Python script (format_cv.py) located in a specific project directory (~/PycharmProjects/career-lexicon-builder). This is used to perform the core document formatting and PDF preview generation. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted resume content from the user and processes it through an LLM to generate structured JSON.
- Ingestion points: Raw CV/resume text provided by the user in Step 1 of the workflow.
- Boundary markers: None identified; there are no explicit delimiters or instructions for the agent to ignore instructions embedded within the user's resume content.
- Capability inventory: The skill has the ability to execute shell commands via
subprocess.runand write files to the local file system (e.g.,/tmp/cv_mapping.jsonand output.docxfiles). - Sanitization: No explicit sanitization or validation of the input text is performed before it is analyzed by the LLM or passed to the generation script.
Audit Metadata