The Agent Skills Directory

[PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data (source code) through the use of tools like Read and Grep. This constitutes an indirect prompt injection attack surface where malicious instructions embedded in comments or strings within the audited code could attempt to influence the agent's behavior.
Ingestion points: The skill uses Read, Grep, and Glob tools to ingest content from files in the environment for analysis.
Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the audited code content as untrusted data or to ignore embedded instructions.
Capability inventory: The skill has access to Bash, Read, Grep, and Glob tools.
Sanitization: No sanitization, escaping, or validation of the ingested code content is specified before the agent processes it.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool and Grep to search for specific forbidden code patterns (e.g., empty catch blocks). This use of shell commands is routine for its stated purpose of auditing codebases and enforcing standards.

silent-failure-hunter