cover-letter-generator

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from resume files and LinkedIn job postings, creating a surface for indirect prompt injection. 1. Ingestion points: Resume text extracted via scripts/extract_resume.py and job descriptions retrieved via Playwright. 2. Boundary markers: The skill does not specify delimiters or 'ignore embedded instructions' warnings for the extracted data. 3. Capability inventory: The skill executes shell commands (python3) and performs network operations (LinkedIn research). 4. Sanitization: There is no evidence of filtering or sanitization of the external content before processing.
  • [COMMAND_EXECUTION]: The skill executes a local Python script scripts/extract_resume.py to extract text from user-provided .docx files. While intended, this involves running a subprocess with a variable file path input.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 01:31 PM
Security Audit — agent-trust-hub — cover-letter-generator