competitor-analysis
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze content from 2-5 external competitors based on user-provided names and URLs. This creates a surface where malicious instructions embedded in competitor websites or metadata could influence the agent's behavior during the synthesis and recommendation phases.
- Ingestion points: Competitor names and URLs provided as arguments to the command or via interactive user prompts are used to fetch external data (Step 2-7).
- Boundary markers: There are no explicit instructions or delimiters mentioned to isolate the external competitor content from the agent's system instructions or to warn the agent about potentially malicious embedded content.
- Capability inventory: The skill has read access to local brand profiles, guidelines, and agency SOPs located in the
~/.claude-marketing/directory. - Sanitization: The skill description does not specify any sanitization, filtering, or safety checks performed on the external content before it is processed by the analysis agents.
Audit Metadata