jira
Fail
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill's metadata for Linux installation employs a piped shell pattern:
curl -fsSL https://raw.githubusercontent.com/ankitpokhrel/jira-cli/master/scripts/install.sh | sh. This executes an external script directly on the host system without prior verification. - [EXTERNAL_DOWNLOADS]: The skill downloads an installer from a third-party GitHub repository (
ankitpokhrel/jira-cli) that is not identified as a trusted or well-known vendor in the system configuration. - [PROMPT_INJECTION]: The skill ingests untrusted content from Jira issues, creating a vulnerability surface for indirect prompt injection.
- Ingestion points:
SKILL.md(viajira issue listandjira issue viewcommands) - Boundary markers: Absent; there are no delimiters or instructions to ignore potential commands embedded in Jira issue content.
- Capability inventory: The skill can execute shell commands via the
jiraCLI and modify issue data (commenting, assigning). - Sanitization: Absent; no filtering or escaping is applied to the Jira data before it enters the agent context.
Recommendations
- HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/ankitpokhrel/jira-cli/master/scripts/install.sh - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata