landing-optimizer
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, such as landing page content, influencer messages, and promotional claims, creating a surface for indirect prompt injection.
- Ingestion points: The skill reads landing page URLs, influencer messages, and platform content provided by the user or external connectors (SKILL.md, Step 1).
- Boundary markers: The instructions do not define explicit delimiters or warnings to separate untrusted data from the agent's internal instructions.
- Capability inventory: The skill's primary capabilities involve reading local memory files (
memory/claims/offers.md) and writing optimization plans to the local filesystem (SKILL.md, Step 2 and Handoff Summary). - Sanitization: There is no evidence of sanitization, validation, or filtering of the external content before it is processed by the agent.
- [NO_CODE]: The skill consists exclusively of Markdown documentation, YAML metadata, and structured templates. It does not include any scripts (e.g., Python, JavaScript), binaries, or automated package installation steps.
Audit Metadata