The Agent Skills Directory

[SAFE]: The skill uses allowed tools to read project-specific documentation such as docs/prd.md and docs/research.md to fulfill its core purpose of strategic planning.
[SAFE]: Web search and fetching capabilities are utilized for legitimate market research and pricing benchmarking.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for indirect prompt injection as it processes data from external project files without explicit boundary markers or sanitization.
Ingestion points: docs/prd.md, docs/research.md, and CLAUDE.md are read during the initial steps.
Boundary markers: None are specified to separate ingested content from the agent's internal instructions.
Capability inventory: The skill has access to file read/write tools and network search tools (WebSearch, WebFetch, mcp__searxng__web_search).
Sanitization: No validation or filtering logic is present for the data read from project files.
[SAFE]: All identified MCP tools (mcp__solograph__kb_search, mcp__solograph__project_info) are associated with the author's ecosystem and represent expected functionality.

solo-launch