skills/michaeltarasov02/skills/update/Gen Agent Trust Hub

update

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the GitHub CLI command gh issue list --assignee=@me to retrieve tasks assigned to the user from repositories.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its extensive processing of untrusted data from external sources.\n
  • Ingestion points: Data is ingested from GitHub issues, external project trackers (Jira, Asana), chat messages, sent emails, calendar events, and recently modified documents via MCP sources.\n
  • Boundary markers: The instructions lack delimiters or explicit warnings for the agent to ignore instructions that might be embedded within the external tasks, emails, or chat messages being processed.\n
  • Capability inventory: The skill has the capability to write to and update sensitive local files, including TASKS.md and files within the memory/ directory (such as people/, projects/, and glossary.md).\n
  • Sanitization: There is no evidence of content validation or escaping of the retrieved external text before it is used to suggest or perform memory and task updates.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 12:22 PM
Security Audit — agent-trust-hub — update