social-signal-bot
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for monitoring untrusted external data such as social media mentions, replies, and DMs. This creates a surface where an attacker could embed malicious instructions in their replies to influence the agent's behavior.
- Ingestion points: Monitoring of mentions, replies, and DMs described in the 'Workflow' and 'Monitoring' sections of SKILL.md.
- Boundary markers: The skill recommends using an 'allowlist for interactions' to limit exposure to unknown users.
- Capability inventory: Automated posting to platforms like X and Telegram, and monitoring of incoming messages.
- Sanitization: The instructions advise implementing 'preflight checks' for banned words and 'avoiding auto-engaging with scams'.
Audit Metadata