T09 · Insecure Skill Coding Practices
- Location
scripts/learner.py:61- Finding
Symlink-Following Arbitrary File Overwrite in Learning-State Storage
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed research workflow with a local learning-state helper, with no evidence of exfiltration or destructive intent.
Install only if you are comfortable with a Chinese-language research helper that may create research files and keep local learning history. Run the learner only against trusted skill directories, avoid elevated privileges, and keep research outputs in a dedicated workspace.
scripts/learner.py:61Symlink-Following Arbitrary File Overwrite in Learning-State Storage
The skill claims a sophisticated research, verification, orchestration, and self-evolving workflow, but the finding indicates the actual implemented behavior is materially different and centers on local persistence of learning statistics and preferences. This mismatch is dangerous because users and orchestrators may grant trust, autonomy, or access based on the declared purpose while the real behavior performs undisclosed stateful data retention, undermining transparency and consent.
The skill advertises behavior that writes research artifacts such as outline.yaml, fields.yaml, results/item_N.yaml, and report.md, but it declares no explicit tool scope or permissions boundaries. In agent environments, undeclared file-write capability increases the risk of unintended or overly broad filesystem modifications, making the skill harder to review and constrain safely.
The manifest description is written entirely in Chinese and the rest of the skill documentation also presents the skill in Chinese, with no indication that users may choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified.
This code file contains natural-language descriptions and CLI usage text entirely in Chinese, and later emits Chinese-only user-facing messages. Under the language/locale policy, forcing a specific language without user opt-in is a policy concern unless the locale restriction is explicitly justified.
The script prints status, insight, and reflection messages exclusively in Chinese during normal execution. This enforces a single locale on users without presenting a choice or documenting a justified regional limitation.
This markdown file contains user-facing natural language exclusively in Chinese and does not mention that the language is optional, user-selected, or required for a region-specific purpose. Under the policy, forcing a specific language without opt-in can be a locale policy violation.
The JSON stores the capability name as the Chinese phrase "蒸馏增强" with no accompanying indication that the skill supports multiple languages or that it is intentionally region-specific. Under the policy for natural-language violations, a fixed locale-specific label can be a concern when no opt-in or justification is provided.