pr-description-writer
Warn
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: MEDIUMDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
- [DYNAMIC_EXECUTION]: The script
scripts/pr_body_lint.pydynamically loads therisk_classifier.pymodule at runtime usingimportlib.utilandexec_moduleon a path computed relative to the script file. This dynamic loading from computed paths matches patterns for runtime code execution. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from pull request bodies and diff outputs, which could be exploited to influence agent behavior through indirect prompt injection.
- Ingestion points: The skill fetches external pull request bodies using
gh pr viewand code changes usinggit diff. - Boundary markers: Absent. There are no delimiters or specific instructions for the agent to treat the ingested PR content as untrusted data.
- Capability inventory: The skill can create and modify pull requests on the host behalf using the
gh pr createandgh pr editcommands. - Sanitization: Absent. While
scripts/pr_body_lint.pyscans for secrets, it does not validate or sanitize inputs for malicious instructions or prompt injection patterns. - [CREDENTIALS_UNSAFE]: The file
assets/sample_pr_body_flawed.mdcontains a hardcoded bearer token (Authorization: Bearer eyJhbGci...). Although this is a dummy value provided in a sample file for testing linter functionality, it matches the signature of hardcoded credentials.
Audit Metadata