pricing
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill contains instructions to ingest and analyze external data, which is a potential attack surface for indirect prompt injection.
- Ingestion points: The 'Pricing Page Teardown' section in
SKILL.mddirects the agent to evaluate content fetched from external URLs or provided via pasted text. - Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions that might be embedded within the external data.
- Capability inventory: The skill is composed of markdown instructions and does not execute scripts with system-level capabilities (e.g., file writes, subprocesses).
- Sanitization: There are no requirements for sanitizing or validating the ingested content before the agent processes it.
Audit Metadata