The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the terminal tool to run shell commands including git clone, find, ls, and the pygount CLI tool to inspect codebases.
[COMMAND_EXECUTION]: The target resolution procedure involves interpolating user-supplied repository URLs or directory paths directly into shell command strings (e.g., git clone --depth 50 ). This creates a risk of command injection if the input strings contain shell control characters.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted data from external sources. 1. Ingestion points: File content from external repositories (Steps 2-10). 2. Boundary markers: Absent; there are no instructions to the agent to disregard instructions that might be embedded within the source code being documented. 3. Capability inventory: The agent has access to terminal, read_file, and write_file across all documentation steps. 4. Sanitization: Absent; content is processed directly to generate wiki pages.
[EXTERNAL_DOWNLOADS]: The skill executes network operations to clone repositories from arbitrary URLs provided by the user.

code-wiki