The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute local discovery commands such as find, grep, cat, and ls. These commands search for ML model artifacts (e.g., .pkl, .pt, .h5), training scripts, and configuration files (SKILL.md).
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it reads and processes content from untrusted local project files to generate its assessment report (SKILL.md).
Ingestion points: Files such as requirements.txt, pyproject.toml, .yaml, .json, and .ipynb are ingested via cat and grep.
Boundary markers: The skill does not implement clear delimiters or instructions to the agent to ignore potentially adversarial instructions embedded within the file content.
Capability inventory: The skill has the capability to run shell commands via Bash and access files via Read, Glob, and Grep.
Sanitization: No explicit validation, escaping, or sanitization of the extracted file content is performed before processing.

cortex-recon