dataforseo-backlinks-api

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATIONNO_CODE
Full Analysis
  • Prompt Injection (LOW): The SKILL.md file contains user prompt examples designed to trigger the agent to install the skill (e.g., 'If you don't have the skill installed, install dataforseo-backlinks-api'). This can be used to influence the agent's behavior regarding skill management and bypass explicit user consent for installation.- Data Exposure & Exfiltration (LOW): The skill documentation and REFERENCE.md file describe the transmission of API login and password credentials (HTTP Basic Auth) to api.dataforseo.com. While this is the intended service endpoint, it is not a predefined trusted domain for data transmission.- Metadata Poisoning (LOW): The skill's metadata claims to be generated with 'OpenAI GPT-5.2', which is a non-existent model version. This provides inaccurate and misleading provenance information.- Indirect Prompt Injection (LOW):- Ingestion points: The skill retrieves backlink data and anchor text from the DataForSEO API (api.dataforseo.com) and displays it to the agent.- Boundary markers: No delimiters or instructions to ignore embedded commands within the API response are specified in the integration contract.- Capability inventory: The skill enables the agent to perform outbound network requests and process external data structures.- Sanitization: There are no instructions or mechanisms provided to sanitize or validate the external API payload before it enters the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 03:51 PM