tailrocks-contribute-respond
Warn
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the computer tool to execute
scripts/contribute-respond.ts, which coordinates state transitions and contribution responses. - [DYNAMIC_EXECUTION]: The script
scripts/contribute-respond.tsuses a dynamicimport()call to load thecontribution-stage-coremodule from a relative path (../../../scripts/contribution-stage-core) that traverses outside the skill's directory. This indicates a dependency on external code that is not contained within the audited package. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from pull requests, reviews, and comments, creating a potential attack surface. Capability Tier: High (performs network actions and modifies repository state). Sanitization: Present. The
runtime-trust.mdguidelines explicitly define external content as untrusted data and mandate that it cannot override security constraints or authority. Boundary Markers: None identified in the provided text.
Audit Metadata