competitor-profiling
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from arbitrary competitor websites to generate synthesized profiles.\n
- Ingestion points: Content is retrieved from external URLs via the
firecrawl_scrapeandfirecrawl_maptools as defined inSKILL.md.\n - Boundary markers: Absent; the skill does not instruct the agent to use XML tags or specific delimiters to isolate scraped content from instructions.\n
- Capability inventory: The skill performs file system writes to the
competitor-profiles/directory and executes network-based tool calls via Firecrawl and DataForSEO, all orchestrated inSKILL.md.\n - Sanitization: Absent; there is no logic to filter or sanitize the scraped markdown content before it is used as context for the synthesis phase.\n- [EXTERNAL_DOWNLOADS]: The skill fetches site data and market metrics from well-known services (Firecrawl and DataForSEO). This behavior is legitimate and necessary for the tool's intended competitive research functionality.
Audit Metadata