The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted data from the web, which creates a potential surface for indirect prompt injection.
Ingestion points: Content is retrieved from external websites using WebFetch and from lyric files via the Read tool or MCP functions.
Boundary markers: The instructions do not specify the use of delimiters or specific directives to prevent the agent from following instructions that might be present in the fetched lyrics or web pages.
Capability inventory: The skill has access to WebSearch, WebFetch, Read, Glob, Grep, and the bitwize-music-mcp toolset.
Sanitization: No sanitization or validation of the fetched external text is described before it is analyzed by the model.
[SAFE]: The skill's logic is consistent with its stated purpose of plagiarism detection. All identified tools and MCP extensions (bitwize-music-mcp) are associated with the vendor bitwize-music-studio. No evidence of credential harvesting, malicious persistence, or unauthorized data exfiltration was found.

plagiarism-checker