relay-merge
Warn
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [DYNAMIC_EXECUTION]: The script
scripts/finalize-run.jsdynamically generates a Node.js script as a string and executes it vianode -e(passed as an argument in a command configuration). This behavior is implemented in themergeObserverfunction to verify PR identity.\n- [COMMAND_EXECUTION]: The skill invokes external CLI tools such asgitandgh, along with Node.js scripts, usingexecFileSyncandspawn. It allows binary paths to be overridden through environment variables likeRELAY_GIT_BIN,RELAY_GH_BIN, andRELAY_SPRINT_STATE_BIN, which could lead to the execution of unintended binaries if these variables are manipulated.\n- [DATA_EXFILTRATION]: The skill accesses GitHub authentication tokens from environment variables (GH_TOKEN,GITHUB_TOKEN) to interact with the GitHub API. While intended for legitimate PR operations, this represents a capability for network exfiltration of local repository state. It also reads from and writes to user-local configuration and run data stored in the~/.relaydirectory.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources, including GitHub PR responses, git logs, and local project markdown files.\n - Ingestion points:
scripts/finalize-run.js(GitHub PR API data),scripts/sprint-owner.js(sprint frontmatter and issue body metadata),scripts/append-learnings.js(readingspec/capabilities.md).\n - Boundary markers:
scripts/append-learnings.jsutilizes HTML comment markers (<!-- LEARN:BEGIN -->) to delineate the areas it is authorized to modify.\n - Capability inventory: The skill has the ability to execute commands via
execFileSync, write to files on the local file system, and perform authenticated network operations through theghCLI.\n - Sanitization: The skill performs input validation using regular expressions to check for valid SHAs, PR numbers, and safe tokens.
Audit Metadata