solo-landing-gen

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection through its data processing workflow. It reads project documentation from files that may be influenced by external actors and uses that content to drive agent behavior.
  • Ingestion points: The skill parses prd.md, README.md, and research.md to extract product details, features, and competitors.
  • Boundary markers: Absent. The skill does not utilize delimiters or specific instructions to treat ingested file content as untrusted data.
  • Capability inventory: The agent has access to powerful tools including Bash, Write, Edit, and mcp__solograph__web_search.
  • Sanitization: None. Extracted text is interpolated directly into prompts for generating headlines, copy, and code scaffolding, and is used as queries for web searches.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 01:42 PM