marketing
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection attacks.
- Ingestion points: External data enters the agent context via the WebSearch and WebFetch tools defined in SKILL.md.
- Boundary markers: There are no delimiters or instructions to ignore embedded commands within the fetched external content.
- Capability inventory: The agent can use Read, Write, and Edit tools (SKILL.md), which may allow an attacker to influence the local filesystem through poisoned web content.
- Sanitization: The skill lacks logic for escaping, validating, or filtering external content before processing.
Audit Metadata