The Agent Skills Directory

[SAFE]: The skill provides instructions for the agent to act as a code reviewer. It explicitly includes security checks (Check 8) to detect common vulnerabilities such as hardcoded secrets, unsafe HTML usage, and potential injection vectors in the code being reviewed.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data (source code files provided by the user or other build tools). This presents an indirect prompt injection surface where instructions hidden within comments or strings in the reviewed code could attempt to influence the agent's behavior.
Ingestion points: Reads one or more files just written/modified as specified in the skill's operational description.
Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore embedded commands within the code it reviews.
Capability inventory: The skill generates a text-based quality report. No capabilities for network operations, file system modifications, or shell execution were identified in the instruction set.
Sanitization: There is no evidence of input sanitization or filtering of the content being reviewed.

vibe-coding-code-review