Trust Assessment
paste-rs received a trust score of 79/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Suspicious import: urllib.request, Prompt Injection via `--no-redact` option bypasses data redaction.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Prompt Injection via `--no-redact` option bypasses data redaction The `paste-rs` skill includes a `--no-redact` command-line option that, when used, disables the automatic redaction of common secret patterns (tokens, API keys, passwords). While the skill documentation warns against its use, an adversarial prompt could instruct the host LLM to invoke the `paste-rs` skill with the `--no-redact` flag. This bypasses the intended security measure, leading to the exfiltration of sensitive information that would otherwise be redacted by the skill's built-in safeguards. 1. **Remove or restrict `--no-redact`**: If possible, remove the `--no-redact` option entirely. If it's deemed absolutely necessary for debugging, consider making it accessible only via a specific, highly privileged context or requiring explicit human confirmation. 2. **LLM Instruction Tuning**: Ensure the host LLM's system instructions explicitly forbid the use of `--no-redact` for the `paste-rs` skill, or instruct it to always prioritize redaction unless there's an extremely high-confidence, explicit, and confirmed user intent to share raw secrets. 3. **Agent-side validation**: Implement agent-side validation to prevent the LLM from calling the skill with `--no-redact`. | LLM | scripts/paste_rs.py:120 | |
| MEDIUM | Suspicious import: urllib.request Import of 'urllib.request' detected. This module provides network or low-level system access. Verify this import is necessary. Network and system modules in skill code may indicate data exfiltration. | Static | skills/banghasan/paste-rs/scripts/paste_rs.py:19 |
Scan History
Embed Code
[](https://skillshield.io/report/4fe6c1208490850f)
Powered by SkillShield