blume-update-docs
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The workflow involves executing shell commands such as "blume build", "blume validate", and repository-specific lint/format/typecheck scripts. This is required for validating documentation changes but involves executing logic defined within the target repository.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources like pull request descriptions, changelogs, and external links to determine documentation updates.
- Ingestion points: Recent pull requests, changelogs, external documentation links, and code exports (SKILL.md, Workflow Step 3).
- Boundary markers: None identified in the prompt instructions to isolate untrusted content.
- Capability inventory: File system write access for documentation updates, Git operations (branch, commit, push, PR), and shell command execution for builds and linting.
- Sanitization: No specific sanitization or filtering logic is described for the ingested content.
Audit Metadata