Trust Assessment
continuity 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 Read via --session Argument.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Arbitrary File Read via --session Argument The `cmd_reflect` function allows reading content from an arbitrary file path specified by the `--session` command-line argument. This grants the skill excessive permissions, enabling it to read any file on the system that the process has access to. This could lead to data exfiltration if sensitive files are read and their contents are processed or exposed, for example, by being sent to an external LLM API (as implied by the `analyze_session` function's comments) or included in error logs. Restrict the `--session` argument to only accept file paths from a predefined, secure directory (e.g., a dedicated session log directory). Alternatively, consider passing session content directly as a string argument or through a more controlled input mechanism, rather than allowing arbitrary file paths. | LLM | scripts/continuity.py:169 |
Scan History
Embed Code
[](https://skillshield.io/report/0f402074d89a9878)
Powered by SkillShield