kata-roadmap
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external documents such as initiative requests and product contracts which could contain malicious instructions designed to subvert agent behavior.
- Ingestion points: The skill reads
initiative-request,idea-brief, andproduct-contractfiles from the local repository to establish project roadmaps. - Boundary markers: No specific delimiters or boundary markers (such as XML tags or explicit 'ignore instructions' wrappers) are mentioned to isolate untrusted data from the system prompt.
- Capability inventory: The skill utilizes shell commands via
bw(Beadwork),gh(GitHub CLI), andtwg(Jira CLI), and performs file system writes to update roadmap state. - Sanitization: There is no evidence of input validation or sanitization described for the data being incorporated into roadmap records or command-line arguments.
Audit Metadata