Security Audit
dceoy/speckit-agent-skills:skills/speckit-tasks
github.com/dceoy/speckit-agent-skillsTrust Assessment
dceoy/speckit-agent-skills:skills/speckit-tasks received a trust score of 83/100, 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 Unsafe Shell Command Construction, Path Traversal Risk.
The analysis covered 4 layers: manifest_analysis, llm_behavioral_safety, dependency_graph, static_code_analysis. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 8, 2026 (commit c21d8d2d). 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 | Unsafe Shell Command Construction The skill instructs the LLM to execute a bash script (`check-prerequisites.sh`) and explicitly provides guidance on escaping quotes for arguments. This strongly implies that the LLM is expected to construct shell commands, potentially passing user inputs (like feature names or constraints) as arguments. If the LLM constructs a command string using unsanitized user input, it creates a high risk of command injection. Prohibit the LLM from constructing shell commands with dynamic arguments. Use safer alternatives like passing arguments as a list to a subprocess call (avoiding shell interpretation) or validate/sanitize all inputs against a strict allowlist before use. | Unknown | SKILL.md:18 | |
| MEDIUM | Path Traversal Risk The skill defines file paths using a dynamic `<feature>` variable (e.g., `specs/<feature>/plan.md`) without defining validation logic. If this variable is derived from user input, an attacker could supply path traversal sequences (e.g., `../`) to access files outside the intended directory. Explicitly instruct the LLM to validate that the 'feature' variable contains only safe characters (e.g., alphanumeric) and rejects any input containing path separators or traversal sequences ('../') before constructing file paths. | Unknown | SKILL.md:13 |
Scan History
Embed Code
[](https://skillshield.io/report/a8ceba586ecc67fa)
Powered by SkillShield