wrap-session
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands to inspect the repository state, specifically calling
git status --shortandgit log --oneline -5as part of its verification process. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting untrusted data from the local environment and remote sources.
- Ingestion points: The skill reads configuration from the
AGENTS.mdchain and extracts information from Git logs and GitHub PR/Issue states (documented in sections 2 and 3). - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are specified when reading external data.
- Capability inventory: The skill is authorized to perform file writes (to changelogs, ADRs, and trackers) and execute Git operations including
commitandpush(documented in sections 4 and 6). - Sanitization: There is no evidence of sanitization, validation, or escaping of the content retrieved from external files or GitHub metadata before it is processed by the agent.
Audit Metadata