nirc-badge-request

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it ingests untrusted data from external sources (e.g., pasted text or receipt emails) to automate form-filling tasks.
  • Ingestion points: Step 3 in SKILL.md instructs the agent to process pasted content, tables, or receipt emails from forms-receipts-noreply@google.com provided by the user.
  • Boundary markers: The skill does not provide the agent with explicit instructions or delimiters to isolate embedded instructions that might be present in the ingested data.
  • Capability inventory: The agent has the capability to interact with external websites via browser automation (filling inputs and clicking elements) and can write configuration data to the local file system at ~/.config/nirc_badge_request/config.yaml.
  • Sanitization: No data validation or sanitization processes are defined to filter or verify the content of the ingested data before it is used to drive browser interactions or file writes.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 08:13 PM
Security Audit — agent-trust-hub — nirc-badge-request