Trust Assessment
deepthink received a trust score of 65/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 1 critical, 0 high, 1 medium, and 0 low severity. Key findings include Missing required field: name, Instruction to modify agent's internal operational files.
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 14, 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 | |
|---|---|---|---|---|
| CRITICAL | Instruction to modify agent's internal operational files The skill explicitly instructs the agent to modify its own internal operational files (`HEARTBEAT.md` and `SOUL.md`) by adding specific markdown content. If the agent's system is designed to interpret content within these files as instructions or operational directives, this constitutes a direct prompt injection attempt. An untrusted skill could inject malicious instructions into the agent's persistent memory, influencing its future behavior. This also implies excessive write permissions to the agent's workspace. Agents should never allow untrusted skills to directly modify their internal operational or memory files. Any updates to an agent's persistent state or instructions should be mediated by a trusted component, with strict validation and sanitization, or disallowed entirely for untrusted inputs. | LLM | SKILL.md:298 | |
| MEDIUM | Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter. | Static | skills/addisonhellum/deepthink/SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/cc46f6a4d224f9cb)
Powered by SkillShield