06-positioning
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data which could contain malicious instructions intended to influence the agent's output or actions.
- Ingestion points: The skill reads external data from Notion including competitor matrices (Step 05), market/ICP insights (Step 03), and raw customer feedback/pain points (Step 01 Verbatim). It also references local files like
${CLAUDE_PLUGIN_ROOT}/reference/agency-stages.md. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the ingested data, which increases the risk of the LLM following instructions hidden in the input.
- Capability inventory: The skill is capable of writing the processed results (positioning statements and maturity scores) back to Notion. It also triggers other automated skills in the vendor's ecosystem (
competitor-finder,persona-insights-analysis,gtm-action-thinker). - Sanitization: No specific sanitization, filtering, or validation of external content is mentioned before the data is interpolated into the positioning logic and written to the final output destination.
Audit Metadata