dineway-content-research
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes content from external websites and search engine results.
- Ingestion points: As outlined in
SKILL.md, the agent fetches data from organic SERP results via DataForSEO and crawls competitor or official-source pages using Firecrawl. - Boundary markers: While the instructions call for a "normalized Research payload," there are no specific requirements for the agent to use delimiters (like XML tags or triple quotes) or explicit instructions to ignore commands found within the external data.
- Capability inventory: The agent utilizes the
dineway-toolsanddineway-seo-providerscontracts to perform automated data collection and returns a structured payload to a master pipeline. - Sanitization: The skill focuses on data normalization and source attribution, but it does not specify sanitization or filtering logic to prevent the agent from accidentally executing instructions embedded in the crawled natural language text.
Audit Metadata