The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes several shell commands including git diff, grep, ruff, and mypy to identify modified files and enforce project quality standards. These are standard development tools used for their intended purposes.\n- [EXTERNAL_DOWNLOADS]: The skill dynamically loads supplementary skills from the beagle-python and beagle-ai namespaces (e.g., beagle-python:fastapi-code-review) to handle specialized technology stacks detected during the review process.\n- [PROMPT_INJECTION]: The skill processes untrusted source code, which creates a surface for indirect prompt injection.\n
Ingestion points: Source code files and diffs are ingested via git diff and grep commands as specified in SKILL.md.\n
Boundary markers: There are no explicit instructions or delimiters used to separate the code content from the agent's instructions, potentially allowing embedded malicious comments to influence the agent.\n
Capability inventory: The agent has the ability to execute shell commands and load additional specialized skills, which could be misdirected by instructions hidden in the code being reviewed.\n
Sanitization: Code content is analyzed directly without escaping or validation of potential instructions embedded in comments or strings.

review-python