The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute standard development commands for the environment, specifically referencing tools like cargo fmt, cargo test, cargo clippy, and cargo audit for Rust projects, as well as npm audit and bundle audit for other ecosystems. These are legitimate tools used for verifying code quality and security.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data by reviewing recently changed code and git logs. While this presents an attack surface where malicious instructions could be embedded in the code being reviewed, the skill's purpose is to audit that code for issues.\n
Ingestion points: Analyzes commit ranges, shortlogs, and changed implementation files.\n
Boundary markers: None explicitly defined in the workflow instructions.\n
Capability inventory: Uses Bash for command execution and Read for file access.\n
Sanitization: The skill does not explicitly specify sanitization of the code content before analysis, relying on the agent's internal evaluation capabilities.

post-refactor