developer-workshop-program
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses a manual context management system ('Memory') that stores user-provided task and project information in a local file named
devrel-context.md. This architecture creates a surface for indirect prompt injection if the stored data contains malicious instructions that are later retrieved and executed by the agent.\n- Ingestion points: User responses provided during the 'Interview' section inSKILL.mdare processed and stored.\n- Boundary markers: There are no explicit instructions to use delimiters or ignore embedded commands when reading from thedevrel-context.mdfile.\n- Capability inventory: The skill instructions imply the use of file writing and reading capabilities to maintain long-term memory/state.\n- Sanitization: The instructions do not include requirements for sanitizing or validating user input before it is stored in the persistence file.
Audit Metadata