compact-markdown

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted Markdown content which serves as an indirect prompt injection surface. Malicious instructions embedded in a file being compressed could potentially influence the agent's behavior during the task.\n- Ingestion points: Markdown files and pasted text processed according to instructions in SKILL.md.\n- Boundary markers: Absent. The skill does not specify the use of delimiters (e.g., XML tags) to isolate the data being compressed from the system instructions.\n- Capability inventory: The agent is instructed to write files (<original-name>.min.md) and output text to the user.\n- Sanitization: The skill includes a 'Credential scan' pass to redact secrets but lacks sanitization or validation logic to ignore natural language instructions within the input data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 08:53 AM