Trust Assessment
sapi-tts received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Arbitrary File Write via Output Parameter.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Arbitrary File Write via Output Parameter The skill's `tts.ps1` script accepts an `-Output` parameter (`-o`) which allows specifying an arbitrary file path for the generated WAV file. The script uses `$synth.SetOutputToWaveFile($Output)` without validating or sanitizing the provided path. An attacker controlling this parameter could write a WAV file to any location on the filesystem where the script's execution context has write permissions. This could lead to overwriting critical system files, filling up disk space, or writing to sensitive directories, potentially causing denial of service or data corruption. Implement strict validation for the `-Output` parameter. Restrict output paths to a designated, sandboxed directory (e.g., a subdirectory of `$env:TEMP` or the skill's own workspace). Sanitize the path to prevent directory traversal. Alternatively, remove the ability for the user to specify an arbitrary path and always use the internally generated, safe path. | LLM | SKILL.md:126 |
Scan History
Embed Code
[](https://skillshield.io/report/8797fa93c255e064)
Powered by SkillShield