flow-onboard
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for ingesting and analyzing untrusted external data from repository files such as READMEs, manifests, and CI configurations.
- Ingestion points: The agent is instructed to read external repository metadata and documentation in SKILL.md.
- Boundary markers: There are no explicit delimiters defined to isolate untrusted repository data from the agent's internal reasoning.
- Capability inventory: The workflow relies on standard file reading and CLI command execution capabilities.
- Sanitization: No explicit sanitization or filtering of external content is specified, though the skill mandates a safety-first approach of inspecting scripts prior to execution.
Audit Metadata