Skills
skills/f-labs-io/agent-html-skills/html-skills-stop/Gen Agent Trust Hub

html-skills-stop

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local bash script (scripts/stop.sh) to perform session teardown, which involves process termination (kill) and file removal (rm) from the temporary directory.
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect influence by reading data from a local file and using it as a tool argument.
  • Ingestion points: The variable MONITOR_ID is read from a session-specific file in /tmp via scripts/stop.sh.
  • Boundary markers: Absent; the content is utilized directly as an argument for the TaskStop command without delimiters.
  • Capability inventory: The skill employs shell-based process management and the agent's TaskStop capability to end background monitoring tasks.
  • Sanitization: Absent; the skill assumes the content of the temporary file is a valid and safe task identifier created by its counterpart skill.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 12:58 PM
Security Audit — agent-trust-hub — html-skills-stop