technical-writing
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- COMMAND_EXECUTION (LOW): The skill utilizes
curlfor API requests andgitfor repository analysis, which is standard for technical writing agents.\n- EXTERNAL_DOWNLOADS (LOW): Users are instructed to installrequestsandmarkdown2Python packages. These are common dependencies and do not originate from untrusted sources.\n- PROMPT_INJECTION (LOW): The skill has an indirect prompt injection surface due to its analysis of untrusted codebase contents.\n - Ingestion points: Git history and codebase source files (SKILL.md, Phase 1.3).\n
- Boundary markers: Absent; the skill does not use specific markers to distinguish between instructions and analyzed code.\n
- Capability inventory: File reading/writing, shell command execution (git, python, curl), and network communication.\n
- Sanitization: Content from the codebase is not sanitized or escaped before processing.
Audit Metadata