presentation-slide-outliner

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHPROMPT_INJECTIONCOMMAND_EXECUTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION] (HIGH): The skill is susceptible to Indirect Prompt Injection due to its capability-to-content risk profile. 1. Ingestion points: Processes external user requests and documents for 'presentation slide outliner' tasks. 2. Boundary markers: Absent; there are no instructions to distinguish between data content and agent instructions. 3. Capability inventory: Permitted tools include 'Bash', 'Write', 'Edit', and 'Grep', which provide a high-privilege execution environment. 4. Sanitization: None; the skill does not include any logic to filter or escape malicious instructions embedded in slide content.
  • [COMMAND_EXECUTION] (MEDIUM): The skill requests 'Bash' tool access. While common for development tasks, granting shell access to a text-processing utility without restricted scopes or audited scripts increases the impact of a successful prompt injection.
  • [NO_CODE] (INFO): The skill contains no accompanying implementation code or scripts; it relies solely on the LLM's interpretation of the markdown metadata.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 12:45 PM