project-view-status
Warn
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill defines shell commands for the
ghCLI that include user-controllable placeholders like<number>and<owner>. If the agent populates these placeholders with unsanitized strings containing shell metacharacters (e.g., semicolons or pipes), it could lead to the execution of arbitrary commands on the host system. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from GitHub Projects that could contain malicious instructions designed to influence the agent's behavior during report generation.
- Ingestion points: Data is fetched from external GitHub Project items and field definitions via
gh project item-listandgh project field-listin SKILL.md. - Boundary markers: Absent. The skill does not instruct the agent to ignore or delimit instructions found within the project data.
- Capability inventory: Executes
ghCLI commands to interact with the GitHub API (SKILL.md). - Sanitization: None. The skill processes and aggregates the raw JSON data without filtering for potential prompt injection content.
Audit Metadata