emergency-priority2-receipt

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local script at '${CLAUDE_PLUGIN_ROOT}/skills/_lib/pushover_core.ts' using the bun runtime. This is the primary function of the skill and uses a path internal to the plugin environment.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it interpolates user-controlled strings into shell arguments.
  • Ingestion points: The '--title' and '--message' arguments in the 'bun' command in SKILL.md are designed to receive user-supplied text.
  • Boundary markers: The skill does not use XML tags, delimiters, or explicit instructions to ignore potentially malicious embedded content within the variables.
  • Capability inventory: The skill has shell command execution capabilities via 'bun'.
  • Sanitization: There is no evidence of escaping or validation logic in the skill description to prevent shell character breakout (e.g., using backticks or semicolons to execute additional commands).
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 12:25 AM
Security Audit — agent-trust-hub — emergency-priority2-receipt