competitive-teardown
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection vulnerability surface detected.
- Ingestion points: Untrusted data enters the prompt via the [COMPETITOR NAME/URL] variable in SKILL.md.
- Boundary markers: None. The prompt template does not use delimiters or specify that the agent should ignore instructions embedded within the analyzed content.
- Capability inventory: The risk level depends on the capabilities of the agent using the skill, such as web browsing or file reading.
- Sanitization: No input validation or content filtering is performed by the skill.
Audit Metadata