sdapp-commit
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it analyzes untrusted data from the repository to perform its core functions.
- Ingestion points: The agent reads the output of
git diff --cachedandgit log --oneline -5to understand the code changes and match the project's style (SKILL.md). - Boundary markers: Absent. There are no explicit instructions or delimiters used to separate the content of the code changes from the system instructions, which could allow malicious code comments to influence the agent.
- Capability inventory: The skill has the ability to execute
git addandgit commitcommands, and it can programmatically invoke thesdapp-jira-logskill (SKILL.md). - Sanitization: Absent. The skill does not validate or sanitize the content extracted from the git repository before using it to draft commit messages.
Audit Metadata