serp-feature-sniper
Pass
Audited by Gen Agent Trust Hub on Mar 31, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface identified. The skill processes untrusted data retrieved from external sources, which could contain malicious instructions.
- Ingestion points: Competitor webpage content fetched via
fetch_webpage(Phase 2) and search results viaweb_search(Phase 1). - Boundary markers: Absent. The skill does not implement specific delimiters or 'ignore' instructions for the data fetched from the internet.
- Capability inventory: The skill possesses file-writing capabilities to the local filesystem (under the
clients/directory) and makes network calls to SEO APIs. - Sanitization: Absent. No logic is defined to sanitize or escape external content before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: Fetches SERP data from well-known technology providers such as SerpAPI, Serper.dev, DataForSEO, and ValueSERP. These downloads are performed in the context of official API usage and are documented neutrally.
- [COMMAND_EXECUTION]: Performs local file system operations by saving analysis reports to the
clients/subdirectory. This behavior is aligned with the skill's stated purpose of report generation.
Audit Metadata