internal/tools/builtin/confinement.go ResolveReadable applies exactly the read tool's policy (resolvePath + isReadConfined), which is purely lexical: filepath.Abs/Rel, never EvalSymlinks. A symlink inside the workspace pointing at /etc/shadow passes the check, and the telegram sender then opens att.Path with no confinement check of its own, in a different goroutine after the turn. There is also a real TOCTOU window -- prepare stats/opens/closes, SendMedia re-stats and re-opens later.
The policy is unchanged from the read tool, so this is not a new hole; what changed is the consequence. The read tool caps at 5MB into the operator's own context; send_file ships up to 50MB OUT to a chat. The shell tool has never been confined either, so a model that wants the bytes already has them.
Decide: either resolve symlinks in ResolveReadable (which changes read-tool behaviour too, and may break legitimate symlinked workspaces), or document the caveat explicitly and stop claiming 'sending cannot reach what reading cannot' without it.
Found by adversarial review of 9a45fbb.
Acceptance Criteria
Either the symlink case is closed at the resolver, or the limitation is written down where the claim is made (confinement.go doc comment and sendfile package doc).
Close reason
ResolveReadable now follows symlinks and re-checks the real path (359cf9db); sender opens the symlink-free path.
Imported from beads archie-core-jkmu · GitHub #647 · type task · priority P3 · created 2026-08-24 · closed 2026-10-25
internal/tools/builtin/confinement.go ResolveReadable applies exactly the read tool's policy (resolvePath + isReadConfined), which is purely lexical: filepath.Abs/Rel, never EvalSymlinks. A symlink inside the workspace pointing at /etc/shadow passes the check, and the telegram sender then opens att.Path with no confinement check of its own, in a different goroutine after the turn. There is also a real TOCTOU window -- prepare stats/opens/closes, SendMedia re-stats and re-opens later.
The policy is unchanged from the read tool, so this is not a new hole; what changed is the consequence. The read tool caps at 5MB into the operator's own context; send_file ships up to 50MB OUT to a chat. The shell tool has never been confined either, so a model that wants the bytes already has them.
Decide: either resolve symlinks in ResolveReadable (which changes read-tool behaviour too, and may break legitimate symlinked workspaces), or document the caveat explicitly and stop claiming 'sending cannot reach what reading cannot' without it.
Found by adversarial review of 9a45fbb.
## Acceptance Criteria
Either the symlink case is closed at the resolver, or the limitation is written down where the claim is made (confinement.go doc comment and sendfile package doc).
### Close reason
ResolveReadable now follows symlinks and re-checks the real path (359cf9db); sender opens the symlink-free path.
---
_Imported from beads `archie-core-jkmu` · GitHub #647 · type task · priority P3 · created 2026-08-24 · closed 2026-10-25_
sam
added the lowtask labels 2026-10-27 13:40:14 +00:00
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
internal/tools/builtin/confinement.go ResolveReadable applies exactly the read tool's policy (resolvePath + isReadConfined), which is purely lexical: filepath.Abs/Rel, never EvalSymlinks. A symlink inside the workspace pointing at /etc/shadow passes the check, and the telegram sender then opens att.Path with no confinement check of its own, in a different goroutine after the turn. There is also a real TOCTOU window -- prepare stats/opens/closes, SendMedia re-stats and re-opens later.
The policy is unchanged from the read tool, so this is not a new hole; what changed is the consequence. The read tool caps at 5MB into the operator's own context; send_file ships up to 50MB OUT to a chat. The shell tool has never been confined either, so a model that wants the bytes already has them.
Decide: either resolve symlinks in ResolveReadable (which changes read-tool behaviour too, and may break legitimate symlinked workspaces), or document the caveat explicitly and stop claiming 'sending cannot reach what reading cannot' without it.
Found by adversarial review of 9a45fbb.
Acceptance Criteria
Either the symlink case is closed at the resolver, or the limitation is written down where the claim is made (confinement.go doc comment and sendfile package doc).
Close reason
ResolveReadable now follows symlinks and re-checks the real path (359cf9db); sender opens the symlink-free path.
Imported from beads
archie-core-jkmu· GitHub #647 · type task · priority P3 · created 2026-08-24 · closed 2026-10-25