skills/sirsws/akm/akm-fitness-planner/Gen Agent Trust Hub

akm-fitness-planner

Pass

Audited by Gen Agent Trust Hub on Mar 26, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: No attempts to bypass safety filters or override system instructions were found. The prompts focus on structured information elicitation and adherence to user-provided constraints.
  • [DATA_EXFILTRATION]: No network operations, hardcoded credentials, or access to sensitive local files (e.g., .ssh, .aws) were detected.
  • [REMOTE_CODE_EXECUTION]: The skill does not download or execute any external scripts, packages, or remote code.
  • [COMMAND_EXECUTION]: No shell commands, subprocess calls, or dynamic context injections (!command) are present in the skill files.
  • [OBFUSCATION]: No hidden text, Base64-encoded strings, zero-width characters, or homoglyphs were found.
  • [INDIRECT_PROMPT_INJECTION]: While the skill ingests user fitness data, it lacks risky capabilities such as network access or file writing, mitigating potential exploitation surfaces.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 26, 2026, 01:39 PM
Security Audit — agent-trust-hub — akm-fitness-planner