sales-instapage
Pass
Audited by Gen Agent Trust Hub on Jul 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its interaction with external data sources and persistent local state.\n
- Ingestion points: The skill ingests data from the Instapage API via form submission endpoints and reads the
references/learnings.mdfile at the beginning of each session.\n - Boundary markers: There are no explicit instructions or delimiters defined to help the agent distinguish between untrusted platform data and its own instructions.\n
- Capability inventory: The skill instructions involve network requests using
curland Python'srequestslibrary, and file system modifications for updating the locallearnings.mdfile.\n - Sanitization: No logic for sanitizing or validating external content is specified in the implementation recipes.\n- [SAFE]: The skill adheres to security best practices by using placeholders for API tokens and providing guidance on secure credential management.\n- [SAFE]: All external URLs and resources are official vendor resources belonging to Instapage or the skill author's infrastructure.
Audit Metadata