solo-launch
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues were detected. The skill's behavior, including reading local documentation and performing web searches, is consistent with its stated purpose of providing launch strategy planning and coordination.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted project documentation to generate a strategy document.
- Ingestion points: Reads project-specific data from
docs/prd.md,docs/research.md, andCLAUDE.mdin Step 1. - Boundary markers: Uses structural markdown templates and YAML frontmatter headers to delimit the generated strategy in Step 8.
- Capability inventory: Accesses file system tools (
Read,Write,Grep,Glob), network research tools (WebSearch,WebFetch), and specialized MCP search tools (mcp__solograph__kb_search,mcp__solograph__web_search). - Sanitization: Ingested content is interpolated into the final document without explicit escaping or validation instructions.
Audit Metadata