landing-page-gtm
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as
git logto research feature history and project-specific type-checking tools to validate code quality before shipping updates. These are routine development operations within the skill's defined scope. - [PROMPT_INJECTION]: Identifies an indirect prompt injection surface (Category 8) resulting from the processing of untrusted external content.
- Ingestion points: The skill reads existing landing page content from a user-provided 'Target URL' and evaluates competitive positioning based on external competitor data during Phase 1 and Phase 2.
- Boundary markers: There are no defined boundary markers or explicit instructions to the agent to treat external content as untrusted or to ignore embedded instructions within that content.
- Capability inventory: The agent possesses the ability to read from and write to the local filesystem (SKILL.md Phase 5) and execute shell commands (git, type checkers).
- Sanitization: No sanitization, escaping, or validation mechanisms are implemented for the external content fetched from target URLs before it is incorporated into the agent's reasoning and generation workflow.
Audit Metadata