The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes standard, read-only commands including rg --files, rg -n, and cat on project configuration files like package.json, pyproject.toml, and Cargo.toml. These operations are limited to establishing the repository stack and do not pose a security risk.- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests data from untrusted files within the repository. 1. Ingestion points: Repository configuration files and file contents searched via rg. 2. Boundary markers: None present. 3. Capability inventory: Read-only access to files; no network access or arbitrary code execution capabilities. 4. Sanitization: None present. The risk is assessed as safe because the skill's capabilities are restricted to generating a classification report and do not include high-risk operations.- [SAFE]: No obfuscation, data exfiltration, hardcoded credentials, or persistence mechanisms were detected in the skill instructions.

agent-sort