call-summary

Warn

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on Bash execution to perform tool discovery and call data retrieval via the composio CLI.
  • [PROMPT_INJECTION]: The variable $ARGUMENTS is directly included in the instructions. Since these arguments are intended to be passed into shell commands (such as the call ID in Step 2), a malicious user could supply shell metacharacters like backticks, semicolons, or pipe symbols to execute unauthorized commands.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. Ingestion points: External call transcripts and recordings fetched via API are ingested into the context (SKILL.md, Step 3). Boundary markers: The instructions lack delimiters or explicit directives to treat the transcript content as untrusted data rather than instructions. Capability inventory: The agent has access to a shell environment (composio CLI in SKILL.md). Sanitization: There is no evidence of validation or escaping for the external content before it is processed by the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 1, 2026, 08:14 PM
Security Audit — agent-trust-hub — call-summary