project-view-status
Warn
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill suggests setting
GIT_SSL_NO_VERIFY=1when running in sandbox environments. Disabling SSL/TLS certificate verification allows network traffic to be intercepted or modified by a Man-in-the-Middle (MitM) attacker, which could lead to the exposure of GitHub project data or authentication tokens. - [COMMAND_EXECUTION]: The skill relies on executing shell commands via the GitHub CLI (
gh project) to retrieve project metadata, item lists, and field definitions. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted content from GitHub project items. Ingestion points: Data retrieved from
gh project item-list(item titles, descriptions). Boundary markers: Absent; the instructions do not define delimiters or provide warnings to the agent to ignore instructions embedded in the project data. Capability inventory: The skill has the ability to execute shell commands. Sanitization: Absent; the skill processes external data and interpolates it into the final report without validation or escaping.
Audit Metadata