tailor-resume

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted job descriptions (JDs) from external files or URLs. A malicious JD could contain hidden instructions to manipulate the agent's behavior during the resume rewriting process.
  • Ingestion points: Untrusted job descriptions are ingested via the --jd and --jd-url arguments, or from the crm/opportunities.md file.
  • Boundary markers: The procedure does not specify the use of delimiters or instructions for the agent to ignore instructions embedded within the job description.
  • Capability inventory: The skill utilizes Read and Write tools for file access and limited Bash commands (mkdir, test, date) as specified in the YAML frontmatter.
  • Sanitization: There is no mention of sanitization, validation, or escaping of the job description content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 05:16 AM
Security Audit — agent-trust-hub — tailor-resume