The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external source code using the Read, Grep, and Glob tools. Since the agent is also granted access to the Bash tool in the frontmatter, there is a risk that malicious instructions embedded within the code being reviewed (e.g., in comments or strings) could attempt to influence the agent's behavior.
Ingestion points: The skill uses Read, Grep, and Glob to load external files into the agent's context for review.
Boundary markers: The instructions do not specify the use of delimiters or warnings to the model to ignore potential instructions embedded within the source code being analyzed.
Capability inventory: The skill allows the use of the Bash tool, which provides a high-privilege execution environment if the agent is successfully manipulated.
Sanitization: There are no instructions for sanitizing, filtering, or escaping the content of the code files before they are processed by the agent.

simplicity-reviewer