The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were detected. The skill performs static analysis on codebase files using permitted tools like Grep and Bash.
[COMMAND_EXECUTION]: The skill utilizes Bash for pattern detection within the local environment. This is consistent with the intended functionality of a pattern-matching tool.
[PROMPT_INJECTION]: As an auditing tool, the skill has an attack surface for indirect prompt injection via the code it analyzes. 1. Ingestion points: The skill uses Read, Grep, and Glob tools to ingest project code (SKILL.md). 2. Boundary markers: No explicit boundary markers or instructions to ignore embedded instructions in the audited data are provided. 3. Capability inventory: The skill has access to Bash, Read, Grep, and Glob tools. 4. Sanitization: No sanitization or validation of the ingested code content is specified before processing.

codeprobe-patterns