ot-assess
Pass
Audited by Gen Agent Trust Hub on Nov 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local shell script
../ot-init/scripts/on-track-index.shto validate the project state.\n - Evidence: Step 8 in
SKILL.mdspecifies running a bash script located in a sibling directory relative to the skill's installation.\n- [INDIRECT_PROMPT_INJECTION]: The skill reads and evaluates external content from the target repository, creating a surface for embedded instructions to influence agent behavior.\n - Ingestion points: Reads
on-track/INDEX.mdand repository files (history, commands, behavior) in Step 1 and 3 ofSKILL.md.\n - Boundary markers: Absent; no delimiters or ignore-instructions are specified for the audited content to prevent malicious instructions in data from influencing agent reasoning.\n
- Capability inventory: Capability to write assessment files to the project directory (Step 7) and execute local shell scripts (Step 8).\n
- Sanitization: Absent; the skill does not verify or sanitize the content read from the audited files before processing it.
Audit Metadata