the-lever-finder
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill ingests data from
.agents/product-context.mdand processes direct user input to generate growth plans. This creates an indirect prompt injection surface where malicious instructions embedded in the processed data could influence the agent's reasoning or output. - Ingestion points: The skill reads business metrics and model details from
.agents/product-context.mdand requests user input for revenue, challenges, and channel performance. - Boundary markers: No explicit delimiters or system-level instructions are used to distinguish the untrusted external content from the skill's core instructions.
- Capability inventory: The skill lacks capabilities for file modification, network communication, or code execution; it is restricted to text analysis and generation.
- Sanitization: The skill does not perform validation or sanitization of the input data before integrating it into its analysis process.
- [NO_CODE]: The skill consists exclusively of markdown instruction files and reference documentation. It does not include, download, or execute any Python, Node.js, or shell scripts.
Audit Metadata