community-mod-pack
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [NO_CODE]: The skill is composed entirely of markdown documentation and configuration metadata; no executable scripts, binary files, or installation manifests are included in the package.
- [PROMPT_INJECTION]: The skill processes untrusted user content from Discord and Telegram platforms, presenting an indirect prompt injection surface where malicious instructions in chat messages could potentially influence the agent's output.
- Ingestion points: Message history, channel log exports, and read-only API access for Discord and Telegram as specified in SKILL.md and references/endpoints.md.
- Boundary markers: The instructions do not define specific delimiters or instructional barriers to prevent the agent from following commands embedded within the chat data.
- Capability inventory: The agent's capabilities are limited to ingestion, summarization, and drafting; enforcement actions like banning or deleting are explicitly defined as out of scope.
- Sanitization: No sanitization or validation logic is specified for the messages retrieved from external sources before they are presented to the model.
Audit Metadata