competitive-analysis
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the GitHub CLI (
gh) to retrieve public repository data such as star counts, release lists, and contributor counts. These are read-only operations against a well-known service used for competitive benchmarking. - [EXTERNAL_DOWNLOADS]: The skill employs
WebFetchandWebSearchto gather external market intelligence. This is consistent with its primary purpose of performing competitive and industry analysis. - [DATA_EXFILTRATION]: No patterns of sensitive data exfiltration were found. The network activity is restricted to fetching information for analysis rather than transmitting local secrets.
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests untrusted data from the web and GitHub APIs.
- Ingestion points: Data fetched via
WebFetch,WebSearch, andgh apicalls inSKILL.mdandreferences/competitive-analysis-guide.md. - Boundary markers: None explicitly defined in the templates to separate fetched content from instructions.
- Capability inventory: Subprocess execution via
ghCLI and file system access viaRead,Glob, andGrep. - Sanitization: No explicit sanitization or filtering of external content is documented.
Audit Metadata