saas-launch-audit
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses browser tools (mcp__claude-in-chrome) and WebFetch to ingest content from user-provided URLs for auditing. This ingestion of untrusted data from external sources represents a vulnerability surface for indirect prompt injection.\n
- Ingestion points: URLs for SaaS landing pages, pricing, and legal documents are provided by the user and processed by the agent.\n
- Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for data retrieved from external URLs.\n
- Capability inventory: The skill has access to shell script execution (Bash) and browser automation tools.\n
- Sanitization: There is no defined process for sanitizing or filtering the content retrieved from external sites before processing.\n- [COMMAND_EXECUTION]: The skill includes and executes local shell scripts (scripts/tech-audit.sh and scripts/competitor-visibility.sh) using the Bash tool to automate technical checks and research tasks. These scripts take user-provided input (URLs and product names) as arguments.
Audit Metadata