resume-tailor

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill's README and quick-start guide recommend an installation method that fetches a shell script from the developer's GitHub repository (https://raw.githubusercontent.com/nishilbhave/ats-resume-tailor/main/install.sh) and pipes it directly to the bash interpreter for execution.
  • [COMMAND_EXECUTION]: The provided installation and uninstallation scripts (install.sh and uninstall.sh) utilize shell commands to create directories and copy or delete files within the user's home directory (~/.claude/skills/ and ~/.claude/agents/).
  • [PROMPT_INJECTION]: The skill processes untrusted input from resumes and job descriptions provided by the user as text or file paths. Evidence: 1. Ingestion points: Resume and Job Description content ingested via SKILL.md. 2. Boundary markers: The prompt templates do not implement specific delimiters or 'ignore' instructions for the ingested text. 3. Capability inventory: The skill has file system read access for local files and coordinates text processing across several agents. 4. Sanitization: There is no evidence of text sanitization or filtering applied to the external input before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 11:13 PM
Security Audit — agent-trust-hub — resume-tailor