The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of analyzing external Rust source code.
Ingestion points: The skill uses Read and Grep to ingest content from files matching **/*.rs as specified in the SKILL.md frontmatter.
Boundary markers: The skill lacks explicit boundary markers or instructions to the agent to ignore potentially malicious instructions embedded in the code comments or strings of the files being analyzed.
Capability inventory: Tools provided include Read, Grep, and Glob, which allow the agent to process arbitrary content from the workspace to find unsafe patterns.
Sanitization: There is no evidence of sanitization or filtering of the ingested code content before it is presented to the AI agent for analysis.

unsafe-checker