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, and CLAUDE.md in 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
Risk Level
SAFE
Analyzed
Apr 5, 2026, 09:51 AM