blume-write-skill
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill consists of plain-text instructions and a template for technical writing. No executable scripts, obfuscated payloads, or sensitive data access patterns were identified.
- [COMMAND_EXECUTION]: The workflow mentions using the
blume buildandblume skillCLI tools for verification. These are standard development tools for the Blume platform mentioned in the skill. - [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and process documentation files from the local environment.
- Ingestion points:
blume.config.ts,meta.ts, and project Markdown files. - Boundary markers: Absent. The instructions do not specify the use of delimiters for the external content.
- Capability inventory: The workflow references running the
blume buildandblume skillCLI commands. - Sanitization: Absent. The skill directs the agent to copy content verbatim from the source files.
Audit Metadata