project-guidelines-example
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill defines a logic pattern for processing external data via an LLM that is susceptible to indirect prompt injection.
- Ingestion points: The
contentvariable in theanalyze_with_claudefunction inSKILL.mdis used to pass external data into the LLM context. - Boundary markers: The implementation lacks boundary markers or system instructions to distinguish between developer instructions and user-provided data.
- Capability inventory: The skill utilizes the Anthropic API with tool-calling capabilities in
SKILL.mdto perform structured analysis on input. - Sanitization: No input validation or filtering is performed on the data before it is sent to the LLM.
Audit Metadata