api-attack-surface-mapper

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill is composed entirely of markdown documentation and instructions for an agent workflow. It does not contain any executable scripts, Python files, JavaScript, or binaries.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because its core function involves processing untrusted external data which could contain malicious instructions.
  • Ingestion points: The skill ingests external data from API specifications (OpenAPI URLs/files, Postman collections) and captured network traffic as defined in the 'Required Inputs' section of SKILL.md.
  • Boundary markers: The execution workflow does not define any boundary markers or instructions to the agent to ignore embedded prompts within the ingested specifications.
  • Capability inventory: The skill is configured to perform network operations, including 'Confirm route liveness' and 'baseline validation' against target URLs based on the ingested data.
  • Sanitization: The workflow lacks specified sanitization or validation logic to filter out potentially malicious natural language instructions embedded within the API specifications or traffic data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 10:07 PM