The Agent Skills Directory

[SAFE]: The skill serves as a natural language template and instruction set for tailoring CVs to cybersecurity job descriptions. It does not contain any executable scripts (Python, Node.js, or Shell) or automation tools.
[SAFE]: No network activity, external downloads, or sensitive file access patterns were found. References to security tools like Metasploit, Nmap, and Burp Suite are contextually appropriate as keywords for a penetration testing resume.
[SAFE]: Metadata and descriptions are consistent with the skill's functionality. No prompt injection, obfuscation, or persistence mechanisms were detected.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data (job descriptions and existing CVs) to perform its analysis. However, because the skill has no destructive capabilities (no file writing, no network access, no command execution), the risk is negligible.
Ingestion points: User-provided job description text and CV text processed during Phase 1 and Phase 2.
Boundary markers: None explicitly defined in the instructions.
Capability inventory: No tool use, subprocess calls, or external communication capabilities identified.
Sanitization: None present; the skill relies on the underlying model's safety guardrails.

cv-pentester