presentation-validation

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided markdown files (e.g., PRESENTASJON.md) and extracts content snippets into its validation report. This presents a potential surface for indirect prompt injection if these files contain malicious instructions intended for the agent reading the report. \n
  • Ingestion points: PRESENTASJON.md, AGENDA.md, DISCOVERY.json, and source files within the project folder. \n
  • Boundary markers: The tool outputs structured results in JSON or a formatted human-readable report, aiding the agent in distinguishing report data from file content. \n
  • Capability inventory: The script is restricted to local file reads and writing a report file within the project directory. It does not possess network or dynamic execution capabilities. \n
  • Sanitization: The skill performs structural validation but does not filter or sanitize the text extracted from the project files for prompt injection patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 01:44 PM
Security Audit — agent-trust-hub — presentation-validation