pstack-technical-writing
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and rewrite technical documents, PR descriptions, and commit messages, which are untrusted data sources.
- Ingestion points: Technical documents, PR descriptions, and commit messages (SKILL.md).
- Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the processed text.
- Capability inventory: The analyzed files contain no functional scripts, subprocess calls, network operations, or file-writing capabilities that could be exploited by injected content.
- Sanitization: No sanitization or validation of the input content is defined.
- [EXTERNAL_DOWNLOADS]: The skill references external source code repositories for attribution and maintenance tracking.
- Mentions the canonical source at GitHub under the
cursor/pluginsrepository (UPSTREAM.md). - [SAFE]: The skill primarily consists of instructional documentation and metadata. It does not include executable code or scripts that perform operations on the host system.
Audit Metadata