The Agent Skills Directory

[SAFE]: The skill is a standard code review utility designed to help developers identify bugs and security issues.
The instructions focus on identifying security vulnerabilities such as hardcoded secrets and missing input sanitization in user-provided code.
The skill uses a restricted set of tools (Read, Grep, Glob) for analysis, limiting its scope to read-only operations.
No remote code execution, data exfiltration, or obfuscation patterns were detected.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted code data, which serves as a potential surface for indirect instructions embedded in the analyzed code.
Ingestion points: Code files are accessed using the Read, Grep, and Glob tools referenced in SKILL.md.
Boundary markers: The instructions lack specific delimiters or explicit warnings to the agent to disregard instructions embedded within the code being reviewed.
Capability inventory: The skill's capabilities are limited to read-only operations; it does not possess tools for network communication or file system modification.
Sanitization: The skill does not specify any sanitization or escaping mechanisms for the code content it analyzes.

reviewing-code