update-app-design
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute local commands for project metadata retrieval.
- Evidence:
- Execution of
stat -f "%Sm" .claude/skills/1-app-design-document.mdcto check file modification times. - Execution of
git log --oneline --since="30 days ago" | head -20to analyze recent changes. - Execution of
cpfor creating document backups. - [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8) due to its data ingestion patterns.
- Ingestion points: Reads content from
package.json,.claude/skills/1-app-design-document.mdc, andgit logoutput. - Boundary markers: Absent; there are no specific instructions or delimiters used to ensure the agent ignores instructions embedded within the codebase or documentation files.
- Capability inventory: The skill has access to powerful tools including
Bash,Write, andMultiEdit, which could be exploited if malicious instructions were ingested. - Sanitization: No evidence of sanitization or validation of the content read from the codebase before processing.
Audit Metadata