The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources, specifically GitHub pull request files and metadata. This content is untrusted and could contain malicious instructions designed to influence the agent's behavior during review or merge operations. The skill possesses powerful capabilities that could be abused if such an injection occurs.
Ingestion points: The skill reads pull request files and metadata via mcp__github__get_pull_request_files and gh pr list (found in SKILL.md).
Boundary markers: There are no explicit instructions or delimiters defined to isolate the pull request content from the agent's system prompt or to warn the agent to ignore embedded commands.
Capability inventory: The skill has access to shell execution (Bash), file system modification (Write, Edit), and repository management functions (mcp__github__merge_pull_request, mcp__github__create_pull_request_review).
Sanitization: The skill does not define any sanitization, filtering, or validation logic for the content retrieved from GitHub before it is processed by the agent.
[COMMAND_EXECUTION]: The skill uses the Bash tool to perform legitimate development tasks such as running tests (npm test), checking linting, and interacting with the GitHub CLI (gh). These commands are executed locally in the environment where the agent is running.

agent-pr-manager