competitor-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from competitor websites, which are untrusted external sources. This creates a surface for potential indirect prompt injection attacks where malicious content on those sites could influence agent behavior.
- Ingestion points: Competitor domain data, website content, and URLs identified in
SKILL.mdandreferences/analysis-templates.md. - Boundary markers: The instructions lack explicit delimiters or instructions to ignore embedded commands when processing external content.
- Capability inventory: The skill involves web data collection and references the use of the
domain-authority-auditorCLI tool. - Sanitization: No instructions for sanitizing, validating, or filtering external content are provided in the workflow.
- [COMMAND_EXECUTION]: The
references/analysis-templates.mdfile contains instructions for the agent to execute thedomain-authority-auditorcommand-line tool. While this appears to be a requirement for generating synthesis reports, the use of external tools should be monitored.
Audit Metadata