rodo-dsar-pl

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data subject requests, which represents a potential attack surface. Any instructions hidden within a request could influence the agent's draft.
  • Ingestion points: Text content of incoming DSAR requests processed at runtime.
  • Boundary markers: The instructions do not define explicit delimiters to isolate request content from operational instructions.
  • Capability inventory: The skill uses the Bash tool to execute a local script and has read access to the local file system.
  • Sanitization: The included Python script validates date formats using strict parsing, though the general request text is not specifically filtered.
  • Mitigation: The skill design explicitly mandates that a human administrator performs all sensitive and irreversible actions, such as data export, deletion, or sending the final response, significantly reducing the risk of automated exploitation.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to run a local Python script (scripts/gdpr_deadlines.py). Analysis of the script confirms it is a deterministic calculator with no external dependencies, no network access, and no unsafe dynamic execution (eval/exec) patterns. It only processes date arithmetic.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 07:32 PM
Security Audit — agent-trust-hub — rodo-dsar-pl