skills/am-will/swarms/swarm-planner/Gen Agent Trust Hub

swarm-planner

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core logic of ingesting external data into the agent's context.\n
  • Ingestion points: External documentation is fetched via web search or the Context7 tool (Step 2), and the local codebase is analyzed for architecture and patterns (Step 1).\n
  • Boundary markers: The instructions do not define any delimiters or system-level warnings to distinguish between the skill's instructions and the content of the ingested documentation or code.\n
  • Capability inventory: The skill utilizes file-writing capabilities to save the generated plan (Step 4) and orchestration capabilities to spawn subagents (Step 5).\n
  • Sanitization: There is no evidence of content validation, escaping, or filtering for the external data before it is processed into the final plan.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 09:26 AM
Security Audit — agent-trust-hub — swarm-planner