tek-mark-merge
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from external git branches (specifically the branch
card-<id>) to verify a 'Decision' table and diffs before proceeding with merge operations. This represents an ingestion surface for potentially untrusted data. - Ingestion points: Content and diffs from git branches named
card-<id>(identified inSKILL.md). - Boundary markers: The skill does not use explicit delimiters but includes specific instructional checks to validate the presence of expected headers and evidence before taking action.
- Capability inventory: Git operations including
merge,commit, andpush(identified inSKILL.md). - Sanitization: The instructions include conditional logic to stop execution if the working tree is 'dirty' or if specific evidence requirements are not met.
- [NO_CODE]: The skill consists exclusively of markdown instructions and YAML configuration files. No executable scripts (Python, JavaScript, shell scripts) are included in the skill package.
Audit Metadata