The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands including git diff, git log, and git rev-parse to retrieve repository metadata and source code changes for analysis.
[PROMPT_INJECTION]: The skill processes untrusted external data (code diffs and issue tracker descriptions) which creates a surface for indirect prompt injection attacks.
Ingestion points: Data is ingested from git diff output, git log commit messages, and external specification files or issue trackers via docs/agents/issue-tracker.md.
Boundary markers: The sub-agent prompts interpolate the diff content and spec content directly without the use of strict delimiters or instructions to ignore embedded commands.
Capability inventory: The skill has the capability to execute shell commands via git and spawn parallel sub-agents to process text.
Sanitization: There is no evidence of sanitization or escaping of the ingested code or requirements data before it is passed to the sub-agents.

code-review