candango-wrap-up

Pass

Audited by Gen Agent Trust Hub on May 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs several file-system and command-line operations, including deleting temporary dashboard files such as state.json and index.html, running implementation-specific tests and validation commands, and executing git commands for staging, committing, and creating pull requests via the GitHub CLI.
  • [PROMPT_INJECTION]: The skill demonstrates a vulnerability to indirect prompt injection.
  • Ingestion points: It reads content from potentially untrusted files such as plan.md, issues.md, and uat.md in SKILL.md.
  • Boundary markers: There are no instructions to the agent to treat the content of these files as data only or to ignore embedded instructions.
  • Capability inventory: The skill possesses capabilities that could be abused if an injection is successful, including arbitrary command execution for validation, file deletion, and automated git/GitHub operations as defined in SKILL.md.
  • Sanitization: The skill lacks any mechanism for sanitizing or escaping the content read from external files before it is included in the agent's processing context.
Audit Metadata
Risk Level
SAFE
Analyzed
May 26, 2026, 03:31 PM
Security Audit — agent-trust-hub — candango-wrap-up