The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the repository's git history, diffs, and local documentation files (e.g., in docs/ or specs/). This content is then passed into prompts for sub-agents, creating a surface where malicious instructions embedded in code or comments could attempt to influence the agent's behavior.
Ingestion points: git diff output, git log messages, and the content of specification/standards files (SKILL.md).
Boundary markers: The instructions do not specify the use of clear delimiters or instructions to ignore embedded commands within the diff or spec data passed to sub-agents.
Capability inventory: The skill uses git commands (diff, log, rev-parse) and manages the execution flow of multiple sub-agents (SKILL.md).
Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the repository before it is processed by the AI.
[COMMAND_EXECUTION]: The skill relies on shell command execution to perform repository analysis.
Evidence: Uses git diff, git log, and git rev-parse to identify changes and verify reference points (SKILL.md).

code-review