The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses several shell commands to interact with the local environment, including git, pnpm, and cat. It specifically executes pnpm test, pnpm lint, pnpm tsc, and pnpm dev, which involve running local project scripts that could execute arbitrary code if the repository being reviewed is compromised.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from local source code (via git diff and cat). Maliciously crafted comments or code blocks in the files being reviewed could attempt to override the agent's instructions.
Ingestion points: The skill reads data using git diff HEAD -U15, git status, and cat <file_path> as described in SKILL.md.
Boundary markers: None are defined. The instructions do not provide delimiters or specific guidelines for the agent to separate its own logic from the content of the files it reads.
Capability inventory: The skill has the ability to execute shell commands (git, pnpm) and read local files (cat, git diff) as documented in SKILL.md.
Sanitization: There is no evidence of sanitization, escaping, or filtering of the code content before it is processed by the agent.

local-review