bootstrap-system-context

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. It ingests data from external SAP system APIs (e.g., component descriptions, feature messages) and interpolates them directly into a markdown file (system-info.md) and a chat summary without sanitization or boundary markers.
  • Ingestion points: Outputs from SAPRead, SAPManage, and SAPLint in SKILL.md.
  • Boundary markers: None used in the generation of the system-info.md file.
  • Capability inventory: The skill has the capability to write files to the local project environment.
  • Sanitization: No validation or escaping of external content is performed before interpolation into the output file or chat summary.
  • [DATA_EXFILTRATION]: The skill retrieves and exposes system metadata, including the System ID (SID), client, release version, and the current username. While this information is stored locally in system-info.md and not sent to a remote server by this skill, this data exposure increases the footprint of sensitive environment information.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 11:09 AM
Security Audit — agent-trust-hub — bootstrap-system-context