customerio-security-basics
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements webhook handlers that process external data from Customer.io, which constitutes a potential ingestion point for indirect prompt injection.
- Ingestion points: External webhook payloads are handled in
SKILL.md(Step 3),references/implementation-guide.md(Step 4), andreferences/implementation.md. - Boundary markers: The instructions do not define specific delimiters or boundary markers to isolate untrusted data from the agent's prompt instructions.
- Capability inventory: The skill is granted access to
Write,Edit,Bash, andGreptools, which defines the potential impact of a successful injection attack. - Sanitization: While the skill provides robust PII sanitization (e.g., stripping SSNs and credit card numbers), it does not perform sanitization specifically targeted at preventing prompt injection markers in the ingested payloads.
Audit Metadata