skillshare-codebase-audit
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands like
grep,ls,wc,sort, andheadto analyze the project directory and file contents. These commands are used solely for read-only auditing tasks.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the codebase, which could contain instructions designed to influence the agent's behavior.\n - Ingestion points: Reads data from
cmd/skillshare/*.go,website/docs/commands/*.md,specs/*.md, andinternal/config/targets.yaml.\n - Boundary markers: Absent. The skill does not provide delimiters to separate the audit instructions from the content of the files being audited.\n
- Capability inventory: Uses
grep,ls,wc,sort, andheadvia subprocess calls. The skill is documented as read-only and does not include tools for network access or file modification.\n - Sanitization: No validation or escaping is applied to the data retrieved from the audited files.
Audit Metadata