The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted content from a user-specified project directory to perform its compliance audit.
Ingestion points: The skill reads file contents from the project path provided in $ARGUMENTS using the Read, Grep, and Glob tools.
Boundary markers: The instructions do not define specific delimiters or guardrails to help the agent distinguish between its instructions and potentially malicious commands embedded as strings or comments within the audited project files.
Capability inventory: The skill utilizes Bash, Read, Grep, Glob, and Agent tools, giving it significant access to the file system and shell execution.
Sanitization: The skill does not implement explicit sanitization or filtering of the content extracted from the user's files before it is processed by the agent.
Note: This surface is an inherent part of the skill's primary function as a code auditor and is assessed as safe in this context.

appstore-review