competitor-analysis
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a Python script (
firecrawl.py) located within the platform's plugin root (${CLAUDE_PLUGIN_ROOT}/scripts/connectors/) to perform scraping, mapping, and searching of competitor domains. - [EXTERNAL_DOWNLOADS]: The skill facilitates the fetching of content from arbitrary external competitor URLs provided by the user or discovered during the analysis process.
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface by processing untrusted data from external websites.
- Ingestion points: Competitor content is fetched via the
firecrawl.pyconnector and converted to markdown for the agent to process (SKILL.md). - Boundary markers: The instructions do not define explicit delimiters or warnings to ignore instructions embedded within the scraped content.
- Capability inventory: The agent has the ability to execute shell commands (via the firecrawl connector) and write analysis files to the local
memory/directory. - Sanitization: There is no evidence of sanitization or filtering of the scraped markdown content before it is interpolated into the agent's context.
Audit Metadata