wk-pr-update
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
Bashto interact with the local Git environment and the GitHub CLI (gh). This includes fetching remote updates, managing branch state, and pushing changes. These operations are essential to the skill's purpose. - [DYNAMIC_EXECUTION]: The skill performs automated ecosystem detection to run validation tests (e.g.,
npm test,pytest). While this executes code defined in the project repository, it is gated by the skill's logic to ensure the branch is stable after integration. - [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from pull request bodies and commit messages during the update and synchronization process.
- Ingestion points: Data is ingested through
gh pr viewandgit logcommands inSKILL.md(Stage 1 and Stage 6). - Boundary markers: The skill does not explicitly define delimiters for external text, though it uses standard command-line flags and pipes for processing.
- Capability inventory: The agent has access to
Bash,Write, andAskUserQuestiontools. - Sanitization: GitHub API responses are handled via
jqto select specific fields, reducing the risk of processing malicious payloads in metadata.
Audit Metadata