flow-planify

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data which could contain malicious instructions.
  • Ingestion points: The agent is instructed to read ticket.md and its attachments, and to perform targeted web searches to understand best practices (SKILL.md).
  • Boundary markers: There are no instructions to use delimiters or "ignore instructions" wrappers when processing content from the ticket or web search results.
  • Capability inventory: The skill has the capability to write files to the workspace (.task/<KEY>/<sujet>/plan-<sujet>.md) and invoke several external tools/skills including flow-review, flow-journal, and flow-build (SKILL.md).
  • Sanitization: The skill lacks explicit sanitization or validation steps for the content retrieved from external sources before using it to generate the task plan or trigger tool executions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 03:14 PM
Security Audit — agent-trust-hub — flow-planify