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.mdand 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 includingflow-review,flow-journal, andflow-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