The Agent Skills Directory

[METADATA_POISONING]: The skill's homepage and file footers reference 'https://chen.media', which is flagged as malicious (Blacklisted) by security scanners. This URL has no clear connection to the verified vendor 'alexyc9381'.\n- [DATA_EXFILTRATION]: The skill allows the agent to read arbitrary file paths provided by the user after the '/mock-interview' command. This could be exploited to read sensitive local files such as configuration files or private keys.\n- [EXTERNAL_DOWNLOADS]: The skill fetches content from user-provided URLs for job posts without any validation or filtering, which may lead to ingestion of malicious content or SSRF.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (job posts and resumes) and passes them to multiple sub-agents without boundary markers or sanitization.\n- Ingestion points: Job post URLs, file paths, and pasted text; optional resume files.\n- Boundary markers: Absent; the data is interpolated directly into instructions for the sub-agent panel.\n- Capability inventory: The skill possesses file read, network fetch, and file write (to .mock-interview/) capabilities.\n- Sanitization: None; there is no validation of the external content before it is processed by the sub-agents.

mock-interview