skills/leonardo-picciani/dataforseo-agent-skills/dataforseo-content-analysis-api/Gen Agent Trust Hub
dataforseo-content-analysis-api
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- PROMPT_INJECTION (HIGH): The skill is vulnerable to Indirect Prompt Injection (Category 8). Evidence: 1. Ingestion points: Untrusted content is ingested from external domains, URLs, and keywords as specified in
SKILL.md. 2. Boundary markers: Absent; no delimiters are used to separate external data from instructions. 3. Capability inventory: The agent is instructed to perform network operations and process the results, which allows instructions embedded in external content to potentially control agent behavior or exfiltrate data. 4. Sanitization: Absent; no validation or escaping of external content is performed. - Metadata Poisoning (MEDIUM): The
SKILL.mdmetadata contains deceptive information, claiming the skill was generated with a non-existent 'OpenAI GPT-5.2' model, which misleads users about the skill's origin. - DATA_EXFILTRATION (LOW): The skill makes network calls to
api.dataforseo.com, which is not on the trusted domain list, representing a potential but expected data exposure risk for this service.
Recommendations
- AI detected serious security threats
Audit Metadata