feature-to-posts
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes untrusted data from user-provided links, demos, or screenshots alongside local marketing documentation. ● Ingestion points: User-supplied feature descriptions, external links/media, and local marketing files in
/Users/marclamy/Documents/Code/BlendAI/z-notes/marketing/. ● Boundary markers: The instructions do not define delimiters or provide 'ignore instructions' warnings for the ingested content. ● Capability inventory: The agent is expected to use file-read and browser tools to extract information. ● Sanitization: No validation or filtering logic is specified for the external data sources. - [SAFE]: The skill does not contain any remote code execution patterns, network exfiltration commands, or hardcoded credentials. The use of local file paths is dedicated to retrieving marketing context, and no privilege escalation or persistence mechanisms are present.
Audit Metadata