discourse-forums-playbook
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze forum configurations and content, which introduces a potential surface for indirect prompt injection from processed data. \n
- Ingestion points: The agent ingests user requests regarding forum management, community content, and forum admin settings (SKILL.md). \n
- Boundary markers: The skill uses source-specific labels like
[Discourse]and[Google]for its output, though it lacks explicit delimiters for untrusted input data. \n - Capability inventory: The skill contains no executable scripts, shell commands, or network-capable tools, limiting the potential impact of any injection. \n
- Sanitization: No specific data sanitization or validation routines are defined within the instruction set. \n- [NO_CODE]: The skill consists exclusively of Markdown documentation and JSON configuration files. It does not include any Python, Node.js, or shell scripts. \n- [SAFE]: The analysis did not find any evidence of prompt injection, data exfiltration, obfuscation, or other malicious patterns. The instructions specifically advise against deceptive practices like seeding forums with fake accounts or AI-generated spam.
Audit Metadata