tailrocks-record-decision
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data which creates a surface for indirect prompt injection attacks.
- Ingestion points: The skill reads
roadmap/<slug>/README.md, research artifacts, and web content. - Boundary markers: Instructions in
SKILL.mdandreferences/runtime-trust.mdexplicitly tell the agent to treat external content as evidence, not instructions. - Capability inventory: The skill can write files and perform Git commit/push operations.
- Sanitization: The agent is instructed to flag embedded instructions.
- [COMMAND_EXECUTION]: The skill performs Git operations (
commit,push) to manage roadmap items on specific branches.
Audit Metadata