instagram-multi-account

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection surface identified in the DM outreach automation logic within SKILL.md.\n
  • Ingestion points: Data from external Instagram profiles (such as first names and post topics) is ingested to populate message templates.\n
  • Boundary markers: The instructions do not include delimiters or specific prompts to ensure the agent ignores or sanitizes instructions that might be embedded in the external content.\n
  • Capability inventory: The skill uses this data to perform automated outreach and engagement actions, such as sending direct messages.\n
  • Sanitization: There is no logic or instruction to escape or validate the external data before it is interpolated into the agent's prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 04:09 PM
Security Audit — agent-trust-hub — instagram-multi-account