cowork-qbr-builder

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Potential for Indirect Prompt Injection.
  • Ingestion points: The skill ingest untrusted data from various client artifacts, including emails and support tickets, specified in SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the ingested data as non-executable text or to ignore embedded instructions.
  • Capability inventory: The skill utilizes the Bash, Read, Write, and Grep tools to manipulate files and generate the final report.
  • Sanitization: No sanitization or filtering logic is defined for the content extracted from the client artifacts, allowing potentially malicious instructions in an email to influence the agent's behavior during the reconstruction or drafting phases.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 06:05 PM
Security Audit — agent-trust-hub — cowork-qbr-builder