apiiro-demonstrate-secure-prompt

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the apiiro guardian secure-prompt command-line utility to process generated security prompts.
  • [DYNAMIC_EXECUTION]: Shell commands are constructed at runtime by interpolating strings generated from an analysis of the repository's frameworks, data models, and API patterns.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from local repository files to contextually tailor its generated prompts, which are then passed to a CLI tool.
  • Ingestion points: Analyzes local source code, configuration files, and directory structure.
  • Boundary markers: Absent; there are no instructions provided to the agent to ignore or delimit potentially malicious instructions embedded within the codebase being analyzed.
  • Capability inventory: The skill has the ability to execute shell commands (apiiro guardian secure-prompt) and write to the filesystem (docs/secure-prompt-examples.csv).
  • Sanitization: No specific sanitization or escaping logic is defined for the repository content before it is included in command arguments.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 12:11 PM