tactic-portfolio
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read
.agents/marketing-context.mdto establish evidence-based constraints. While this represents a data ingestion surface, the risk is negligible as the skill lacks capabilities for network communication, file modification, or command execution. Evidence: ingestion point in SKILL.md; no specific boundary markers; capability inventory limited to text generation; no sanitization specified.\n- [SAFE]: The skill strictly follows its defined purpose of strategic analysis and includes explicit safety guidelines prohibiting autonomous actions like spending or publishing without authorization. The metadata and referenced materials are consistent and authored by a recognized vendor.
Audit Metadata