competitor-profiling
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill integrates with well-known services (Firecrawl and DataForSEO) to perform web scraping and SEO data retrieval. This behavior is consistent with the skill's stated purpose and uses official MCP tool patterns for data collection.
- [LOW]: Indirect Prompt Injection: The skill is susceptible to indirect prompt injection because its core functionality involves ingesting untrusted content from external URLs provided by the user.
- Ingestion points: Raw markdown content returned from
firecrawl_mapandfirecrawl_scrape(documented in SKILL.md and references/tool-reference.md). - Boundary markers: Absent; the instructions do not explicitly direct the agent to ignore instructions embedded within the scraped website data.
- Capability inventory: The agent can write files to the local
competitor-profiles/directory and perform further network requests via the scraping/SEO tools. - Sanitization: No evidence of content filtering or sanitization of the scraped data before processing.
Audit Metadata