The Agent Skills Directory

[PROMPT_INJECTION]: No instructions attempting to bypass safety filters or override agent behavior were found. The skill uses standard instructional language to guide resume diagnosis.- [DATA_EXFILTRATION]: No network activity, hardcoded credentials, or sensitive file access (such as .ssh or .aws) were identified. The skill only processes resume data provided by the user in the context of a conversation.- [REMOTE_CODE_EXECUTION]: No external package installations or remote script execution patterns (e.g., curl|bash) were detected.- [INDIRECT_PROMPT_INJECTION]: The skill processes user-uploaded resumes which are untrusted data ingestion points. Evidence Chain: 1. Ingestion points: Triggered by CV file uploads or text input in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: The skill has no capabilities to execute code, access the network, or write files. 4. Sanitization: Absent. The risk is assessed as safe given the lack of exploitable capabilities.- [COMMAND_EXECUTION]: No shell command execution or dynamic command injection patterns were found.

career-resume-diagnosis