competitor-profiling
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes data from untrusted external sources.
- Ingestion points: The skill uses
firecrawl_scrapeandfirecrawl_searchto ingest content from arbitrary competitor URLs and third-party review sites (G2, Capterra, etc.). - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the scraping logic.
- Capability inventory: The skill allows the agent to read local project files (e.g.,
.agents/product-marketing.md) and write new files to the local file system under thecompetitor-profiles/directory. - Sanitization: The instructions lack specific requirements for sanitizing or escaping the content retrieved from external pages before it is processed by the AI.
- [EXTERNAL_DOWNLOADS]: The skill utilizes well-known external services (Firecrawl and DataForSEO) to gather website content and SEO metrics. These are documented as core functionalities of the skill.
Audit Metadata