guard-defend-renewal
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's workflow is built around ingesting and analyzing potentially untrusted external data, which could be used to deliver malicious instructions. * Ingestion points: In references/input-rules.md, the skill is instructed to accept "conversational dump, messy notes, Slack pastes, CRM tables, PDFs, screenshots, voice-to-text". * Boundary markers: There are no instructions for the agent to use specific delimiters or to disregard instructions found within these inputs. * Capability inventory: The skill primarily produces text-based renewal assessments and playbooks; no dangerous system capabilities or network actions are explicitly documented in the provided files. * Sanitization: There is no mention of input sanitization or filtering logic to handle adversarial content in the provided documentation.
Audit Metadata