The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to run local scripts such as ./scripts/review-skill.sh and ./scripts/check-versions.sh for its automated review process. These scripts are part of the skill package and rely on the execution environment's shell.
[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to read and analyze other skills, which exposes it to indirect prompt injection if the files being audited contain malicious instructions. 1. Ingestion points: Data is pulled from external skills using Read, Glob, and Grep tools. 2. Boundary markers: The instructions lack specific requirements for boundary markers to prevent the agent from following instructions embedded in audited code. 3. Capability inventory: The skill has access to powerful tools including Bash, Edit, Write, and WebFetch. 4. Sanitization: No explicit sanitization or filtering of audited content is described.
[METADATA_POISONING]: The skill documentation contains inconsistencies; while the system identifies the author as dennislee928, the skill's README and repository links point to a different maintainer (jezweb) and repository.

skill-review