solo-content-gen
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a shell command to retrieve recent commit history for release notes generation.
- Evidence:
git log --oneline --since="1 month ago" 2>/dev/null | head -20(Step 5). - [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from various project documentation files to generate promotional content and release notes, creating a surface for indirect instructions to influence the agent.
- Ingestion points: The skill reads from
docs/prd.md,README.md,CLAUDE.md, andresearch.md(Steps 1 & 2). - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the prompt templates.
- Capability inventory: The skill has the ability to write files via the
Writetool (Step 6) and execute shell commands (Step 5). - Sanitization: No sanitization, escaping, or validation of the ingested file content is performed before processing.
Audit Metadata