Trust Assessment
startclaw-optimizer 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 Missing required field: name, Prompt Injection via Unsanitized User Input to LLM.
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 Unsanitized User Input to LLM The `generateSummary` function constructs an LLM prompt by directly concatenating user-controlled `messages` content into the prompt string. This allows an attacker to inject malicious instructions into the LLM, potentially overriding system instructions, extracting sensitive information, or manipulating the LLM's behavior. The `content` variable, derived from `messages`, is embedded directly into the Anthropic API call's user message. Implement robust input sanitization or validation for user-provided messages before they are incorporated into LLM prompts. Ideally, use structured input for the LLM where user content is clearly separated from system instructions (e.g., by using distinct message roles for user input and system instructions, or by employing a dedicated tool/function call mechanism for user-provided data). Avoid direct string concatenation of untrusted input into critical prompt sections. | LLM | context-compaction.js:105 | |
| 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/smartpeopleconnected/token-optimizer/skills/startclaw-optimizer/SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/297e1573becb821c)
Powered by SkillShield