skills/clawlink-hq/skills/tally/Gen Agent Trust Hub

tally

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on shell commands using npx to interact with the ClawLink CLI and Tally service for managing forms and webhooks.- [EXTERNAL_DOWNLOADS]: The skill's setup and usage instructions use npx, which automatically fetches the @useclawlink/cli package from the NPM registry at runtime.- [REMOTE_CODE_EXECUTION]: The execution of npx @useclawlink/cli downloads and runs remote code within the agent's environment, creating a dependency on the integrity of the NPM package.- [INDIRECT_PROMPT_INJECTION]: The skill defines tools that process external data from Tally, such as form responses, which could contain instructions designed to manipulate the agent's behavior.
  • Ingestion points: tally_get_form_responses, tally_get_form_details, and tally_list_form_questions tools as described in SKILL.md.
  • Boundary markers: Absent; no specific instructions or delimiters are provided to the agent to ignore instructions embedded in the form data.
  • Capability inventory: Shell command execution via npx (documented in SKILL.md) allows the agent to perform various write and read operations based on processed data.
  • Sanitization: Absent; there is no mention of filtering or validating the content retrieved from Tally.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 05:46 PM