recruiting-ops

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a shell command (ls) to enumerate directories within the user's home folder (e.g., ~/.claude/skills/) to discover installed companion skills from the same author.
  • [EXTERNAL_DOWNLOADS]: The skill suggests the installation of additional modules from the vendor's repository using the npx skills add AbsolutelySkilled/AbsolutelySkilled command.
  • [PROMPT_INJECTION]: The skill is designed to process untrusted external data such as resumes, job descriptions, and candidate messages, creating a surface for indirect prompt injection.
  • Ingestion points: User-provided resumes, job descriptions, and candidate communications are processed by the agent (SKILL.md, references/job-description-templates.md).
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are specified for processing these inputs.
  • Capability inventory: The skill utilizes shell command execution (ls) and supports package installation (npx).
  • Sanitization: There is no evidence of sanitization, escaping, or validation of external content provided in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 01:05 PM
Security Audit — agent-trust-hub — recruiting-ops