roadmap-reality-checker
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted project data (roadmaps and sprint plans), which introduces a risk of indirect prompt injection where malicious instructions could be hidden in the processed content.
- Ingestion points: External roadmaps and sprint plans processed according to instructions in SKILL.md.
- Boundary markers: None; the instructions do not include specific delimiters or warnings to ignore embedded content.
- Capability inventory: None; the skill does not specify or use tools for network access, file writing, or command execution.
- Sanitization: None; there are no instructions for sanitizing or validating the input data.
Audit Metadata