Trust Assessment
observability received a trust score of 78/100, 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, Excessive Permissions Declared.
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 15, 2026 (commit 1823c3f6). 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 | Excessive Permissions Declared The skill declares 'Bash', 'Write', and 'Edit' permissions in its manifest. These permissions grant the agent broad capabilities, including arbitrary command execution and filesystem modification. While potentially necessary for an agent designed to implement complex observability systems (e.g., deploying configurations, running diagnostic commands), these permissions significantly increase the attack surface and risk of privilege escalation, data exfiltration, or data loss if the agent is compromised or misused. The skill's primary content in SKILL.md is descriptive and does not directly utilize these permissions in a malicious way, but their declaration is a fundamental security concern. Review the necessity of 'Bash', 'Write', and 'Edit' permissions. If the skill's core function can be achieved with more restricted permissions (e.g., 'Read' only for documentation, or specific API calls instead of 'Bash'), reduce the scope of declared tools. If these permissions are truly required, ensure robust input validation and execution safeguards are in place for any operations that leverage them, and consider whether the agent's scope of operation can be limited (e.g., containerization, least privilege). | Static | Manifest (frontmatter JSON):1 | |
| 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 | plugins/specweave-infrastructure/skills/observability/SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/bf3302459ab7882d)
Powered by SkillShield