The Agent Skills Directory

[SAFE]: No security threats or malicious patterns were detected. The skill's logic is confined to providing career advice and generating formatted text based on user input.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data such as existing CVs and job descriptions, which represents a potential attack surface. However, the risk is negligible as the skill has no access to sensitive capabilities like shell execution, network requests, or file-system writing.
Ingestion points: SKILL.md (Step 1: Gather Information) and references/input_schema.md detail how the agent should ingest user-provided professional history and external job descriptions.
Boundary markers: The instructions do not explicitly mandate delimiters or guardrails to isolate user data from the system prompt.
Capability inventory: The skill utilizes text generation only. No subprocesses, network calls, or file-writing tools are referenced or requested in the instructions.
Sanitization: There is no evidence of sanitization or filtering of user-provided content.

resume-writer