unblocked-context-search-issues

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to construct and execute a CLI command using the unblocked tool. This command incorporates user-provided inputs for the query and instruction parameters. Without explicit instructions for the agent to escape these inputs, there is a risk of command injection if the user provides malicious shell metacharacters. Evidence: unblocked context-search-issues --query in SKILL.md.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it retrieves and processes content from external issue trackers which are attacker-controllable sources.
  • Ingestion points: Data from Jira, GitHub Issues, Linear, and Asana via the context_search_issues tool.
  • Boundary markers: Absent; there are no instructions to the agent to ignore or delimit instructions found within retrieved issue data.
  • Capability inventory: Shell command execution via the unblocked CLI and project file access via tools like Grep, Glob, and Read.
  • Sanitization: Absent; retrieved issue descriptions and comments are processed as natural language without sanitization or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 04:58 PM
Security Audit — agent-trust-hub — unblocked-context-search-issues