nightly-eval-investigation
Pass
Audited by Gen Agent Trust Hub on Nov 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from evaluation results stored in a Google Cloud Storage bucket (
gs://guidance-evals/). Specifically, thescripts/investigate.tsscript extracts error messages and check IDs fromevals.jsonfiles and includes them in a generated markdown report. Because the agent is subsequently instructed to perform qualitative deep-dives on this report, malicious content in the evaluation output could attempt to influence the agent's diagnostic reasoning. - Ingestion points: Reads
evals.jsonfrom GCS inscripts/investigate.ts. - Boundary markers: The generated report uses standard markdown headings but lacks specific delimiters to isolate untrusted error strings from the agent's instructions.
- Capability inventory: The skill can read/write local files, execute shell commands via
execSync(gcloud, node, gh), and create GitHub issues. - Sanitization: The script performs minimal sanitization, extracting raw message strings for inclusion in the report.
- [COMMAND_EXECUTION]: The skill relies on
child_process.execSyncto perform its core functions. It executesgcloud storagecommands to list and synchronize evaluation results from GCS, andghCLI commands to create parent and sub-issues on GitHub, manage labels, and integrate with GitHub Projects. - Evidence:
scripts/investigate.tsrunsgcloud storage lsandgcloud storage rsync. - Evidence:
scripts/publish_report.tsrunsgh issue create,gh label create,gh project item-add, andgh api graphql. - Context: These commands are necessary for the skill's workflow and target the author's official infrastructure (GoogleChrome GitHub organization and associated GCS buckets).
Audit Metadata