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 content variable in the analyze_with_claude function in SKILL.md is 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.md to 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
Risk Level
SAFE
Analyzed
Mar 14, 2026, 05:23 PM