project-update-items

Warn

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill suggests using GIT_SSL_NO_VERIFY=1 when running in a sandbox environment. This environment variable disables SSL/TLS certificate verification for Git-related operations, making the network connection vulnerable to Man-in-the-Middle (MitM) attacks and potential interception of sensitive data.
  • [PROMPT_INJECTION]: The skill processes project item titles and descriptions retrieved from GitHub, creating an Indirect Prompt Injection surface. Malicious content within a GitHub project item could attempt to influence the agent's behavior during the review or execution phase.
  • Ingestion points: Item titles and field values retrieved via gh project item-list in Step 3.
  • Boundary markers: Absent. There are no instructions for the agent to treat external project content as untrusted data or to use specific delimiters.
  • Capability inventory: gh project item-edit (modification of GitHub Project data).
  • Sanitization: Absent. The skill does not describe methods for escaping or validating project content before it is processed or displayed.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 16, 2026, 09:50 PM