The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze code documentation, which involves ingesting untrusted source code and text files. This creates a surface where malicious instructions could be embedded in the code being analyzed. The skill's configuration allows for broad tool access including shell execution, which could be targeted by such injections.\n
Ingestion points: External source code, API documentation, and technical guides analyzed by the tool as described in the overview and use cases.\n
Boundary markers: The skill instructions do not define specific delimiters or warnings to ignore instructions embedded in the analyzed data.\n
Capability inventory: Access to Bash(cmd:*), Read, Write, Edit, and Grep tools as defined in the skill's frontmatter.\n
Sanitization: There is no evidence of input sanitization or validation logic for the content of the files being analyzed.

code-documentation-analyzer