doc-coauthoring
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches context from official service integrations (Slack, Google Drive) and references a trusted repository (github.com/anthropics) for project attribution. These operations are neutral and consistent with a documentation workflow.
- [COMMAND_EXECUTION]: The skill uses standard file manipulation tools, including
create_fileandstr_replace, to build and refine document sections based on user feedback. - [INDIRECT_PROMPT_INJECTION]: The skill manages a data ingestion surface where external content is processed. 1. Ingestion points: User info-dumps, external links, and team messaging channels (SKILL.md). 2. Boundary markers: None defined. 3. Capability inventory: Writing files (
create_file), editing text (str_replace), and spawning sub-agents for testing (SKILL.md). 4. Sanitization: Not specified. While this presents an injection surface, it is consistent with the skill's primary purpose and contains no malicious patterns.
Audit Metadata