Trust Assessment
prompt-log received a trust score of 30/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 4 findings: 1 critical, 3 high, 0 medium, and 0 low severity. Key findings include File read + network send exfiltration, Sensitive path access: AI agent config, Potential Command Injection via user-supplied arguments to shell script.
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 Findings4
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/thesash/prompt-log/SKILL.md:26 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/thesash/prompt-log/SKILL.md:26 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.clawdbot/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/thesash/prompt-log/SKILL.md:27 | |
| HIGH | Potential Command Injection via user-supplied arguments to shell script The skill's primary function involves executing a shell script (`scripts/extract.sh`) with user-controlled arguments, including the session file path (`<session-file>`) and an optional output path (`--output`). If these arguments are not rigorously sanitized and properly quoted within the `extract.sh` script before being passed to internal commands (such as `jq`, `gdate`, `date`, or other shell utilities), an attacker could inject arbitrary shell commands. This could lead to unauthorized execution of code on the host system. Review the `scripts/extract.sh` file to ensure all user-supplied arguments are properly sanitized and quoted (e.g., using `"$VAR"` or `printf %q` in bash) when passed to `jq`, `date`, or other commands to prevent shell metacharacter interpretation and command injection. | LLM | SKILL.md:10 |
Scan History
Embed Code
[](https://skillshield.io/report/383289088b27a406)
Powered by SkillShield