skills/rade-nugroho/agentic-enteprises-skill/community-executive-escalations-program-manager/Gen Agent Trust Hub
community-executive-escalations-program-manager
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to monitor and process untrusted external data, creating a surface for indirect prompt injection attacks.
- Ingestion points: The skill ingests data from external community sources including forum threads, GitHub issues, social media posts, and Discord messages as described in
references/community_escalation_playbook.mdandreferences/intake_triage_matrix.md. - Boundary markers: The instructions do not specify the use of delimiters or clear boundary markers (e.g., XML tags or triple quotes) when the agent processes or interpolates this untrusted data into its context.
- Capability inventory: The skill is designed to facilitate the drafting of public responses, executive briefings, and decision logs based on the ingested content.
- Sanitization: There are no explicit instructions for the agent to sanitize, escape, or ignore embedded instructions within the community-sourced data before using it to generate outputs.
Audit Metadata