Trust Assessment
session-cleaner received a trust score of 82/100, 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 Arbitrary File Read via Unvalidated Command Line Argument, Sensitive Directories Configurable via Environment Variables.
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 12, 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 | Arbitrary File Read via Unvalidated Command Line Argument The `session-cleaner.mjs` script directly uses `process.argv[2]` as a file path without sufficient validation or sanitization. While `path.resolve` is used, it does not restrict the path to a safe directory. If the skill is invoked directly by an agent with user-controlled input for the `<session-file.jsonl>` argument, an attacker could provide a path to any file on the system (e.g., `/etc/passwd`, `/root/.ssh/id_rsa`). The script will then read the content of this arbitrary file using `fs.readFileSync`, leading to a data exfiltration vulnerability. Although the script attempts to parse the content as JSONL, the act of reading an arbitrary file is a significant security risk. Implement strict validation for command-line arguments. Ensure that any provided file path is restricted to a predefined, safe directory (e.g., by checking if `filePath` is a child of `SESSIONS_DIR`) and that it has the expected `.jsonl` extension. Alternatively, remove the direct file path argument and only allow processing of files discovered by the script itself (e.g., via `--all`, `--yesterday` options). | LLM | session-cleaner.mjs:136 | |
| MEDIUM | Sensitive Directories Configurable via Environment Variables The `SESSIONS_DIR` and `OUTPUT_DIR` are initialized using `process.env.SESSIONS_DIR` and `process.env.OUTPUT_DIR` respectively. If an attacker can manipulate the environment variables of the process running this skill, they could redirect the script to read session files from arbitrary locations or write processed markdown files to arbitrary locations. This could lead to unauthorized data access (reading sensitive files from unexpected locations) or data tampering/exfiltration (writing potentially sensitive processed data to attacker-controlled locations). Avoid using environment variables for sensitive paths that could be controlled by untrusted input. If environment variables must be used, ensure they are set by a trusted source and cannot be overridden by user input. Alternatively, validate the paths derived from environment variables to ensure they are within an allowed, sandboxed directory. | LLM | session-cleaner.mjs:16 |
Scan History
Embed Code
[](https://skillshield.io/report/166e26f3e257d833)
Powered by SkillShield