contentful-custom-app-enhancement
Pass
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill incorporates robust security instructions, explicitly warning against exposing tokens or private credentials in client code and advising on the correct, secure methods for reading installation parameters.
- [SAFE]: The skill correctly identifies and references official vendor resources from Contentful, including its primary documentation domains and official GitHub repositories.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external inputs such as bug reports, customer feedback, and support tickets, which inherently creates a surface for indirect prompt injection.
- Ingestion points: External bug reports, support tickets, and feedback processed during the 'Build the Request Context' phase in SKILL.md.
- Boundary markers: The skill does not define explicit delimiters for untrusted input data.
- Capability inventory: The agent is authorized to modify source code, execute build and test scripts, and utilize Contentful-specific management tools.
- Sanitization: While no explicit input sanitization is mentioned, the risk is significantly lowered by the skill's mandatory planning and validation phases, which require manual verification and implementation summaries.
Audit Metadata