planning
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits a potential attack surface for indirect prompt injection by processing external data and using tools to execute shell commands.
- Ingestion points: The clarify workflow in SKILL.md instructs the agent to read user-provided requests and every comment on them to identify requirements.
- Boundary markers: The skill instructions do not specify the use of delimiters or framing techniques to isolate external content from the agent's core instructions.
- Capability inventory: The track and plan workflows in SKILL.md empower the agent to identify and execute repository-specific commands (such as make test, make client, or make migrate) to verify task completion.
- Sanitization: There are no explicit requirements for validating or escaping user-provided text before it is used in generated plans or as part of verification command context.
Audit Metadata