site-architecture
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read external marketing context files from the workspace, creating a potential surface for indirect instructions to influence the agent's behavior.
- Ingestion points: Reads
.agents/product-marketing.md,.claude/product-marketing.md, orproduct-marketing-context.mdfrom the local workspace as instructed in SKILL.md. - Boundary markers: Absent; there are no instructions provided to the agent to treat this data as untrusted or to ignore embedded commands.
- Capability inventory: The skill performs text analysis and generates site structure documentation (ASCII and Mermaid). While it does not explicitly invoke dangerous shell or network tools in the provided scripts, the agent may have access to default platform tools that could be leveraged if the agent is successfully poisoned.
- Sanitization: Absent; the skill does not define methods to sanitize or validate the ingested context data.
Audit Metadata