skills/cosmix/loom/before-after/Gen Agent Trust Hub

before-after

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a workflow that ingests and executes commands from external YAML-based 'loom plans', making it vulnerable to indirect prompt injection.
  • Ingestion points: External 'loom plans' containing 'truths', 'before_stage', and 'after_stage' definitions.
  • Boundary markers: The skill does not provide any boundary markers or instructions to the agent to ignore potentially malicious instructions embedded within the plans.
  • Capability inventory: The skill uses 'Bash', 'Write', 'Edit', and 'Read' tools, allowing for significant system impact.
  • Sanitization: No sanitization, validation, or escaping of the shell commands defined in the plans is prescribed.
  • [COMMAND_EXECUTION]: The skill's primary function is to execute shell commands (e.g., via truths or before_stage fields) using the 'Bash' tool to verify system state transitions. This intended functionality allows for the execution of arbitrary commands provided in the plan configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 12:46 AM