timeline-report
Warn
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: MEDIUMDATA_EXFILTRATIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [DATA_EXFILTRATION]: The skill accesses local application files including
~/.claude-mem/settings.jsonand the~/.claude-mem/claude-mem.dbSQLite database to extract project history and configuration details. - [COMMAND_EXECUTION]: Shell commands such as
curl,git, andbashare executed to perform project environment detection and interact with the local worker API. - [DYNAMIC_EXECUTION]: The skill uses
node -eto execute a script that parses local configuration files at runtime. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted timeline observations and passes them to an LLM subagent for analysis, creating a potential surface for indirect prompt injection.
- Ingestion points: External project observations retrieved from
http://localhost:${WORKER_PORT}/api/context/injectinSKILL.md. - Boundary markers: The timeline content is placed directly into the agent's prompt without specific delimiters or warnings to ignore embedded instructions.
- Capability inventory: The subagent is explicitly instructed to execute
sqlite3commands on the~/.claude-mem/claude-mem.dbdatabase. - Sanitization: There is no evidence of sanitization or filtering of the project observations before they are analyzed.
Audit Metadata