nano-run
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes several shell scripts (
init-config.sh,init-stack.sh,init-project.sh) located within the user's home directory (~/.claude/skills/nanostack/bin/) to initialize the configuration and environment for the user. - [PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection as it ingests data from local project files to determine the project type.
- Ingestion points: Reads contents of
package.json,go.mod, andrequirements.txtas described in Step 2 ofSKILL.md. - Boundary markers: None identified in the prompt instructions when reading these files.
- Capability inventory: The skill can execute local shell scripts and invoke other capabilities like the
thinkandfeatureskills. - Sanitization: No specific sanitization or filtering of the file contents is described before the data is processed by the agent.
Audit Metadata