Skills
skills/otrebu/agents/dev-work-summary/Gen Agent Trust Hub

dev-work-summary

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill uses a local Bash script to automate the execution of git commands within the user's development directory.
  • Evidence: The SKILL.md workflow invokes scripts/scan-repos.sh using the Bash tool.
  • [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from the local filesystem.
  • Ingestion points: scripts/scan-repos.sh reads git commit messages, branch names, and file paths.
  • Boundary markers: Absent. The script output provides data to the agent without explicit delimiters or warnings to ignore embedded instructions.
  • Capability inventory: The skill utilizes Bash to perform filesystem operations and git command execution.
  • Sanitization: No sanitization or filtering is performed on the data retrieved from the git repositories before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:21 PM