instantly-common-errors
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external API failure payloads and responses, creating a potential surface for indirect prompt injection if those responses contain malicious instructions.\n
- Ingestion points: The agent ingests API status codes, error messages, and response bodies during the triage process (SKILL.md).\n
- Boundary markers: Instructions explicitly require the agent to capture "redacted response shapes" and ensure "sensitive fields [are] redacted" (SKILL.md).\n
- Capability inventory: The skill allows the use of
WriteandEdittools, which could be misused if the agent obeys instructions embedded in API responses (SKILL.md).\n - Sanitization: The skill provides strict guidelines to never print or persist credentials and to redact lead data and email content (SKILL.md).
Audit Metadata